{ "all_operator_windows": { "P01-C00-moderate": [ { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.11987238161795156, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9905881019946707, "mode_shares": { "NONE": { "attention": 0.1007462687465188, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8471040152242396, "moe_router": 0.008477215998495907, "norm_elementwise": 0.034119643236757626, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.13605518456441312, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0019444790834074754, "moe_gemm": 0.8102627123318585, "moe_router": 0.01080794700368473, "norm_elementwise": 0.03163704570787867, "sampler": 0.0 } }, "mode_steps": { "NONE": 3, "PIECEWISE": 5 }, "other_share": 0.009411898005329294, "representativeness": { "smd": { "decode_batch_size": 2.4721524781047854, "mode_FULL": -0.2325584995849942, "mode_NONE": 0.3041456447839143, "mode_PIECEWISE": -0.24468169875030038, "prefill_fraction": 0.18099057277285577, "scheduled_tokens": 0.4474608400278538 }, "valid": false }, "shares": { "attention": 0.11987238161795156, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0010532842927605177, "moe_gemm": 0.8271478398184453, "moe_router": 0.009739725006365179, "norm_elementwise": 0.032774871259148075, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1567.9510000000005, "name": "triton_poi_fused_3" }, { "duration_us": 933.1070000000002, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 827.689, "name": "triton_red_fused_2" }, { "duration_us": 33.057, "name": "triton_poi_fused_2" }, { "duration_us": 22.368999999999996, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 17.247, "name": "triton_red_fused_1" }, { "duration_us": 11.647999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783848264235733542.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.008867955248024707, "attention_mixed": 0.11302508576620553, "attention_prefill": 0.0 }, "classifiable_fraction": 0.990127660582764, "mode_shares": { "FULL": { "attention": 0.16315875281832684, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0031741793017298413, "moe_gemm": 0.7536332801624461, "moe_router": 0.02179864485086512, "norm_elementwise": 0.045434533244984684, "sampler": 0.0 }, "NONE": { "attention": 0.09828250109360281, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8488043657595763, "moe_router": 0.008302816259724543, "norm_elementwise": 0.0348733229605455, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.1472178594517614, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.002166218689199354, "moe_gemm": 0.7946960932441856, "moe_router": 0.012792489660640699, "norm_elementwise": 0.033466283510587794, "sampler": 0.0 } }, "mode_steps": { "FULL": 1, "NONE": 3, "PIECEWISE": 4 }, "other_share": 0.009872339417236002, "representativeness": { "smd": { "decode_batch_size": 1.4422983740600546, "mode_FULL": 0.3594518697735859, "mode_NONE": 0.3041456447839143, "mode_PIECEWISE": -0.49598146699059914, "prefill_fraction": -0.3699982864929203, "scheduled_tokens": 0.1504241077629697 }, "valid": false }, "shares": { "attention": 0.12189304101423025, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0010615972550528194, "moe_gemm": 0.8214241451495896, "moe_router": 0.010879021850869232, "norm_elementwise": 0.034869855313022065, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1449.5139999999994, "name": "triton_poi_fused_3" }, { "duration_us": 884.6050000000004, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 826.8859999999994, "name": "triton_red_fused_2" }, { "duration_us": 30.943000000000005, "name": "triton_poi_fused_2" }, { "duration_us": 22.431999999999995, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 17.441, "name": "triton_red_fused_1" }, { "duration_us": 11.328999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783848305040542105.pt.trace.json.gz" } ], "P01-C00-saturation": [ { "attention_subshares": { "attention_decode": 0.24646421810404764, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9913999320344749, "mode_shares": { "FULL": { "attention": 0.24646421810404764, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0018861985126382374, "moe_gemm": 0.6957077658710443, "moe_router": 0.012274637353427154, "norm_elementwise": 0.03506711219331752, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.008600067965525126, "representativeness": { "smd": { "decode_batch_size": 0.658013698411068, "mode_FULL": 0.6877531107808548, "mode_NONE": -0.6802380609168648, "mode_PIECEWISE": -0.08229232202065807, "prefill_fraction": -0.6816133519618747, "scheduled_tokens": -0.6333120429828512 }, "valid": false }, "shares": { "attention": 0.24646421810404764, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0018861985126382374, "moe_gemm": 0.6957077658710443, "moe_router": 0.012274637353427154, "norm_elementwise": 0.03506711219331752, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1013.7599999999983, "name": "triton_poi_fused_3" }, { "duration_us": 701.0369999999989, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 598.1809999999995, "name": "triton_red_fused_2" }, { "duration_us": 25.409, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 22.721999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 13.697, "name": "triton_red_fused_1" }, { "duration_us": 13.632, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783847491175653217.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.0033278995815980927, "attention_mixed": 0.07664950781433502, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9882022706147409, "mode_shares": { "FULL": { "attention": 0.2372289894559244, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001973103373413011, "moe_gemm": 0.7024833850537113, "moe_router": 0.0127233500493961, "norm_elementwise": 0.03660441698068597, "sampler": 0.0 }, "NONE": { "attention": 0.07774006222398774, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8628349211839768, "moe_router": 0.004560917765838791, "norm_elementwise": 0.04302637544092451, "sampler": 0.0 } }, "mode_steps": { "FULL": 1, "NONE": 7 }, "other_share": 0.011797729385259094, "representativeness": { "smd": { "decode_batch_size": -1.184350878588216, "mode_FULL": -1.8269976055369814, "mode_NONE": 1.8429476277592753, "mode_PIECEWISE": -0.08229232202065807, "prefill_fraction": 1.7302789555698612, "scheduled_tokens": 1.471377771158277 }, "valid": false }, "shares": { "attention": 0.0799774073959331, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 2.7679120945085497e-05, "moe_gemm": 0.8605854751478055, "moe_router": 0.0046754221316145424, "norm_elementwise": 0.04293628681844257, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 13829.692000000014, "name": "triton_poi_fused_3" }, { "duration_us": 6941.902000000004, "name": "triton_red_fused_2" }, { "duration_us": 6363.376999999999, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 297.34499999999997, "name": "triton_poi_fused_2" }, { "duration_us": 147.58499999999998, "name": "triton_red_fused_1" }, { "duration_us": 24.673, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 15.264999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783847533554126659.pt.trace.json.gz" } ], "P01-C01-moderate": [ { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.09652918148381516, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9901512141928626, "mode_shares": { "NONE": { "attention": 0.08897688209726898, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8575678619411076, "moe_router": 0.00844824275387592, "norm_elementwise": 0.035009188256680354, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.11530968327931657, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001889902178480346, "moe_gemm": 0.830686715724326, "moe_router": 0.011422443441794888, "norm_elementwise": 0.031213089133518845, "sampler": 0.0 } }, "mode_steps": { "NONE": 5, "PIECEWISE": 3 }, "other_share": 0.009848785807137474, "representativeness": { "smd": { "decode_batch_size": 0.9854889320929141, "mode_FULL": -0.5993507732751886, "mode_NONE": 1.1348233880978151, "mode_PIECEWISE": -0.7069751104796668, "prefill_fraction": 0.8188657544214422, "scheduled_tokens": 1.1521871833461559 }, "valid": false }, "shares": { "attention": 0.09652918148381516, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0005420276773630952, "moe_gemm": 0.8498582961156129, "moe_router": 0.009301249385245966, "norm_elementwise": 0.033920459530825446, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1815.9390000000008, "name": "triton_poi_fused_3" }, { "duration_us": 1066.9890000000005, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 990.7689999999997, "name": "triton_red_fused_2" }, { "duration_us": 38.336, "name": "triton_poi_fused_2" }, { "duration_us": 21.344, "name": "triton_red_fused_1" }, { "duration_us": 20.768, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 11.296999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783838883939067909.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.006726776525469258, "attention_mixed": 0.09532695434384081, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9902577441629138, "mode_shares": { "FULL": { "attention": 0.14374966861821964, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0032887654854086147, "moe_gemm": 0.7722281273880269, "moe_router": 0.02184573687437963, "norm_elementwise": 0.04582940754683107, "sampler": 0.0 }, "NONE": { "attention": 0.08786076611447088, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8586892334129893, "moe_router": 0.008388182084023156, "norm_elementwise": 0.03506617147547036, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.11217913793023779, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001786978933831843, "moe_gemm": 0.8363300944674595, "moe_router": 0.010036162117713828, "norm_elementwise": 0.03050524878909313, "sampler": 0.0 } }, "mode_steps": { "FULL": 1, "NONE": 3, "PIECEWISE": 4 }, "other_share": 0.009742255837086222, "representativeness": { "smd": { "decode_batch_size": 0.7899190491545085, "mode_FULL": -0.07663743346636, "mode_NONE": 0.5619254019326344, "mode_PIECEWISE": -0.4409586407032101, "prefill_fraction": 0.2296273370258069, "scheduled_tokens": 0.8462072381054137 }, "valid": false }, "shares": { "attention": 0.10205373086931008, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0010046539011378537, "moe_gemm": 0.843998403683613, "moe_router": 0.009802509795881178, "norm_elementwise": 0.03339844591297178, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1620.390000000002, "name": "triton_poi_fused_3" }, { "duration_us": 980.7070000000003, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 882.1790000000001, "name": "triton_red_fused_2" }, { "duration_us": 34.656, "name": "triton_poi_fused_2" }, { "duration_us": 20.480999999999998, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 19.329, "name": "triton_red_fused_1" }, { "duration_us": 11.488999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783838927022053880.pt.trace.json.gz" } ], "P01-C01-saturation": [ { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.13796857782087196, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9898086965802668, "mode_shares": { "NONE": { "attention": 0.13796857782087196, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8097353073456708, "moe_router": 0.005662986065242196, "norm_elementwise": 0.03644182534848179, "sampler": 0.0 } }, "mode_steps": { "NONE": 8 }, "other_share": 0.0101913034197332, "representativeness": { "smd": { "decode_batch_size": -0.8655364049171133, "mode_FULL": -0.6056347203602891, "mode_NONE": 0.6248229775281566, "mode_PIECEWISE": -0.1297191892430149, "prefill_fraction": 0.6919360042362913, "scheduled_tokens": 0.8182182157919601 }, "valid": false }, "shares": { "attention": 0.13796857782087196, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8097353073456708, "moe_router": 0.005662986065242196, "norm_elementwise": 0.03644182534848179, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 4331.866000000005, "name": "triton_poi_fused_3" }, { "duration_us": 2358.544999999997, "name": "triton_red_fused_2" }, { "duration_us": 2195.539, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 92.25900000000001, "name": "triton_poi_fused_2" }, { "duration_us": 51.296, "name": "triton_red_fused_1" }, { "duration_us": 25.217, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.408, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783838155733630380.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.2400737379378586, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9913784351134121, "mode_shares": { "FULL": { "attention": 0.2400737379378586, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001883134648982493, "moe_gemm": 0.7024243548240628, "moe_router": 0.012220876164257787, "norm_elementwise": 0.03477633153825034, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.008621564886587925, "representativeness": { "smd": { "decode_batch_size": 3.1158472389796006, "mode_FULL": 3.2983798616544977, "mode_NONE": -3.197086914213414, "mode_PIECEWISE": -0.1297191892430149, "prefill_fraction": -3.24128548180199, "scheduled_tokens": -2.8103428714456196 }, "valid": false }, "shares": { "attention": 0.2400737379378586, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001883134648982493, "moe_gemm": 0.7024243548240628, "moe_router": 0.012220876164257787, "norm_elementwise": 0.03477633153825034, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 982.8509999999973, "name": "triton_poi_fused_3" }, { "duration_us": 705.1959999999982, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 592.7990000000009, "name": "triton_red_fused_2" }, { "duration_us": 25.921, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 22.368999999999996, "name": "triton_poi_fused_2" }, { "duration_us": 14.016999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 12.417, "name": "triton_red_fused_1" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783838206570748178.pt.trace.json.gz" } ], "P01-C10-moderate": [ { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.07690712187247944, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9897759832839516, "mode_shares": { "NONE": { "attention": 0.07690712187247944, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8669760431839948, "moe_router": 0.009429489436313557, "norm_elementwise": 0.03646332879116368, "sampler": 0.0 } }, "mode_steps": { "NONE": 8 }, "other_share": 0.010224016716048499, "representativeness": { "smd": { "decode_batch_size": 1.7903696522371881, "mode_FULL": -1.4371597160911773, "mode_NONE": 1.4371597160911769, "mode_PIECEWISE": 0.0, "prefill_fraction": 1.5249388209670753, "scheduled_tokens": 1.6614670732013832 }, "valid": false }, "shares": { "attention": 0.07690712187247944, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8669760431839948, "moe_router": 0.009429489436313557, "norm_elementwise": 0.03646332879116368, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1890.1099999999983, "name": "triton_poi_fused_3" }, { "duration_us": 1095.9750000000006, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 1058.7089999999996, "name": "triton_red_fused_2" }, { "duration_us": 40.384, "name": "triton_poi_fused_2" }, { "duration_us": 22.752000000000002, "name": "triton_red_fused_1" }, { "duration_us": 20.032000000000004, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 11.072, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783838884504530948.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.049266143541160906, "attention_mixed": 0.08377752045067025, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9891853536707774, "mode_shares": { "FULL": { "attention": 0.15457303786338591, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003489366068720859, "moe_gemm": 0.7587034266365785, "moe_router": 0.022859966949438017, "norm_elementwise": 0.046720964018498824, "sampler": 0.0 }, "NONE": { "attention": 0.12297149131658515, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8225726880507142, "moe_router": 0.012431913811185054, "norm_elementwise": 0.0325372503493313, "sampler": 0.0 } }, "mode_steps": { "FULL": 4, "NONE": 4 }, "other_share": 0.01081464632922258, "representativeness": { "smd": { "decode_batch_size": 24.775039622970557, "mode_FULL": -0.015698813991273975, "mode_NONE": 0.015698813991273868, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.0963234706088523, "scheduled_tokens": 0.051398685719152515 }, "valid": false }, "shares": { "attention": 0.13304366399183115, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0011121448603552246, "moe_gemm": 0.8022160188398926, "moe_router": 0.015755585066310956, "norm_elementwise": 0.03705794091238747, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 922.1419999999987, "name": "triton_poi_fused_3" }, { "duration_us": 640.8700000000005, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 594.631000000001, "name": "triton_red_fused_2" }, { "duration_us": 21.12, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 19.169, "name": "triton_poi_fused_2" }, { "duration_us": 13.408999999999999, "name": "triton_red_fused_1" }, { "duration_us": 10.721, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783838930721906534.pt.trace.json.gz" } ], "P01-C10-saturation": [ { "attention_subshares": { "attention_decode": 0.17009543151870654, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9841498976767467, "mode_shares": { "FULL": { "attention": 0.17009543151870654, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0039228461117771524, "moe_gemm": 0.7298923248097096, "moe_router": 0.026541989019097344, "norm_elementwise": 0.05369730621745603, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.015850102323253314, "representativeness": { "smd": { "decode_batch_size": 0.346060557246963, "mode_FULL": 0.3620750335204151, "mode_NONE": -0.3620750335204151, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.361159573685948, "scheduled_tokens": -0.3136156264486445 }, "valid": false }, "shares": { "attention": 0.17009543151870654, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0039228461117771524, "moe_gemm": 0.7298923248097096, "moe_router": 0.026541989019097344, "norm_elementwise": 0.05369730621745603, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 668.4249999999997, "name": "triton_poi_fused_3" }, { "duration_us": 540.3219999999997, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 519.6199999999992, "name": "triton_red_fused_2" }, { "duration_us": 20.162, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 14.146, "name": "triton_poi_fused_2" }, { "duration_us": 12.769, "name": "triton_red_fused_1" }, { "duration_us": 10.911999999999997, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783838153027510750.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.18529303661511093, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9842190227520464, "mode_shares": { "FULL": { "attention": 0.18529303661511093, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0039014000835443053, "moe_gemm": 0.7150112365990193, "moe_router": 0.026542171689060874, "norm_elementwise": 0.053471177765311045, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.015780977247953545, "representativeness": { "smd": { "decode_batch_size": 0.346060557246963, "mode_FULL": 0.3620750335204151, "mode_NONE": -0.3620750335204151, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.361159573685948, "scheduled_tokens": -0.3136156264486445 }, "valid": false }, "shares": { "attention": 0.18529303661511093, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0039014000835443053, "moe_gemm": 0.7150112365990193, "moe_router": 0.026542171689060874, "norm_elementwise": 0.053471177765311045, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 670.1069999999988, "name": "triton_poi_fused_3" }, { "duration_us": 540.7329999999994, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 521.2969999999993, "name": "triton_red_fused_2" }, { "duration_us": 19.871, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 14.303999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 12.639, "name": "triton_red_fused_1" }, { "duration_us": 10.815, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783838186373520707.pt.trace.json.gz" } ], "P01-C11-moderate": [ { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.07147321055558287, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9898790022112421, "mode_shares": { "NONE": { "attention": 0.07147321055558287, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8734165832313857, "moe_router": 0.009015253683509436, "norm_elementwise": 0.03597395474076414, "sampler": 0.0 } }, "mode_steps": { "NONE": 8 }, "other_share": 0.010120997788757882, "representativeness": { "smd": { "decode_batch_size": 1.5977202714579513, "mode_FULL": -1.5988956800998717, "mode_NONE": 1.5988956800998717, "mode_PIECEWISE": 0.0, "prefill_fraction": 1.7194658992699898, "scheduled_tokens": 2.889470183704151 }, "valid": false }, "shares": { "attention": 0.07147321055558287, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8734165832313857, "moe_router": 0.009015253683509436, "norm_elementwise": 0.03597395474076414, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1951.778999999998, "name": "triton_poi_fused_3" }, { "duration_us": 1101.107, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 1087.848, "name": "triton_red_fused_2" }, { "duration_us": 41.377, "name": "triton_poi_fused_2" }, { "duration_us": 22.752, "name": "triton_red_fused_1" }, { "duration_us": 19.905, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 11.263999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783849468308907391.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.07815008583685061, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9900845346277651, "mode_shares": { "NONE": { "attention": 0.07815008583685061, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8665104217463119, "moe_router": 0.01003059260991946, "norm_elementwise": 0.035393434434683305, "sampler": 0.0 } }, "mode_steps": { "NONE": 8 }, "other_share": 0.00991546537223486, "representativeness": { "smd": { "decode_batch_size": 3.6469387885636997, "mode_FULL": -1.5988956800998717, "mode_NONE": 1.5988956800998717, "mode_PIECEWISE": 0.0, "prefill_fraction": 1.6333752995057749, "scheduled_tokens": 1.932993318175888 }, "valid": false }, "shares": { "attention": 0.07815008583685061, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8665104217463119, "moe_router": 0.01003059260991946, "norm_elementwise": 0.035393434434683305, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1646.947999999998, "name": "triton_poi_fused_3" }, { "duration_us": 960.6999999999999, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 911.4259999999997, "name": "triton_red_fused_2" }, { "duration_us": 35.168, "name": "triton_poi_fused_2" }, { "duration_us": 20.32, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 19.008, "name": "triton_red_fused_1" }, { "duration_us": 11.325999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783849515320434790.pt.trace.json.gz" } ], "P01-C11-saturation": [ { "attention_subshares": { "attention_decode": 0.016576587438731645, "attention_mixed": 0.07063959803466414, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9887471770371591, "mode_shares": { "FULL": { "attention": 0.16949408215942174, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003719519173496834, "moe_gemm": 0.7347698666441799, "moe_router": 0.02526425285717597, "norm_elementwise": 0.051657468475250934, "sampler": 0.0 }, "NONE": { "attention": 0.07829708337077482, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8654362098361494, "moe_router": 0.006897111319710678, "norm_elementwise": 0.03853325229671188, "sampler": 0.0 } }, "mode_steps": { "FULL": 3, "NONE": 5 }, "other_share": 0.011252822962840962, "representativeness": { "smd": { "decode_batch_size": -0.6805120548902551, "mode_FULL": -0.7994927227550991, "mode_NONE": 0.7994927227550991, "mode_PIECEWISE": 0.0, "prefill_fraction": 0.8067495635539911, "scheduled_tokens": 0.78379501498442 }, "valid": false }, "shares": { "attention": 0.08721618547339578, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0003637704279935639, "moe_gemm": 0.8526569904343553, "moe_router": 0.008693424936188346, "norm_elementwise": 0.03981680576522616, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 2296.86200000001, "name": "triton_poi_fused_3" }, { "duration_us": 1370.555999999998, "name": "triton_red_fused_2" }, { "duration_us": 1296.3929999999978, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 48.382999999999996, "name": "triton_poi_fused_2" }, { "duration_us": 29.056000000000004, "name": "triton_red_fused_1" }, { "duration_us": 20.737, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 11.072999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783848740680228913.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.16100163906049575, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9857318180258278, "mode_shares": { "FULL": { "attention": 0.16100163906049575, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0035030082867205997, "moe_gemm": 0.7487144065958767, "moe_router": 0.023795240157795577, "norm_elementwise": 0.048717523924939055, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.014268181974172239, "representativeness": { "smd": { "decode_batch_size": 0.792348678707734, "mode_FULL": 0.8046290452001797, "mode_NONE": -0.8046290452001796, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.8036484371137015, "scheduled_tokens": -0.761537726891679 }, "valid": false }, "shares": { "attention": 0.16100163906049575, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0035030082867205997, "moe_gemm": 0.7487144065958767, "moe_router": 0.023795240157795577, "norm_elementwise": 0.048717523924939055, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 662.919999999999, "name": "triton_poi_fused_3" }, { "duration_us": 536.0999999999999, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 521.2559999999994, "name": "triton_red_fused_2" }, { "duration_us": 21.152, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.952, "name": "triton_poi_fused_2" }, { "duration_us": 12.287999999999998, "name": "triton_red_fused_1" }, { "duration_us": 10.974999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783848781627748251.pt.trace.json.gz" } ], "P02-C00-moderate": [ { "attention_subshares": { "attention_decode": 0.16431648329180198, "attention_mixed": 0.040375747240313245, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9899496306808163, "mode_shares": { "FULL": { "attention": 0.2070416346282377, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.002614300625672357, "moe_gemm": 0.72402183586612, "moe_router": 0.017564069072735583, "norm_elementwise": 0.03839442593161487, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.19565666700967585, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0017527292718792177, "moe_gemm": 0.7535224022949394, "moe_router": 0.011441473126433909, "norm_elementwise": 0.02878152643291581, "sampler": 0.0 } }, "mode_steps": { "FULL": 7, "PIECEWISE": 1 }, "other_share": 0.010050369319183737, "representativeness": { "smd": { "decode_batch_size": -0.673985188837054, "mode_FULL": 0.11926397031787984, "mode_NONE": -0.2790993472934029, "mode_PIECEWISE": -0.0171348471830914, "prefill_fraction": -0.13753859346790945, "scheduled_tokens": -0.22985353117145157 }, "valid": false }, "shares": { "attention": 0.20469223053211524, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0024365065962538455, "moe_gemm": 0.7301095783988965, "moe_router": 0.016300609001782734, "norm_elementwise": 0.036410706151768, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 775.5859999999996, "name": "triton_poi_fused_3" }, { "duration_us": 562.3350000000004, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 541.5999999999998, "name": "triton_red_fused_2" }, { "duration_us": 22.592, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 16.384, "name": "triton_poi_fused_2" }, { "duration_us": 12.864999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 12.447999999999999, "name": "triton_red_fused_1" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783850544932244469.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.17098573558976576, "attention_mixed": 0.04244961271753521, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9900472542616138, "mode_shares": { "FULL": { "attention": 0.20867035579310442, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0025849579196340765, "moe_gemm": 0.7236684498934784, "moe_router": 0.017385853018663355, "norm_elementwise": 0.03743160202992195, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.23505546138588368, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0025209396629618792, "moe_gemm": 0.7060220856055816, "moe_router": 0.012259376230707445, "norm_elementwise": 0.035577961118325376, "sampler": 0.0 } }, "mode_steps": { "FULL": 7, "PIECEWISE": 1 }, "other_share": 0.00995274573838624, "representativeness": { "smd": { "decode_batch_size": 14.182091081480554, "mode_FULL": 0.11926397031787984, "mode_NONE": -0.2790993472934029, "mode_PIECEWISE": -0.0171348471830914, "prefill_fraction": -0.20596870108215656, "scheduled_tokens": -0.2935716394203467 }, "valid": false }, "shares": { "attention": 0.21343534830730096, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0025733966047573075, "moe_gemm": 0.7204816218764769, "moe_router": 0.016460041922970896, "norm_elementwise": 0.03709684555010769, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 767.5569999999994, "name": "triton_poi_fused_3" }, { "duration_us": 572.6729999999994, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 527.8730000000002, "name": "triton_red_fused_2" }, { "duration_us": 22.624999999999996, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 16.192999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 12.735999999999999, "name": "triton_red_fused_1" }, { "duration_us": 11.902999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783850578506315216.pt.trace.json.gz" } ], "P02-C00-saturation": [ { "attention_subshares": { "attention_decode": 0.3066236078963298, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9922817455017883, "mode_shares": { "FULL": { "attention": 0.3066236078963298, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0016715827167837374, "moe_gemm": 0.6421673334694945, "moe_router": 0.010874019669713833, "norm_elementwise": 0.030945201749466352, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.007718254498211715, "representativeness": { "smd": { "decode_batch_size": 0.20138501290112165, "mode_FULL": 0.20658265838024312, "mode_NONE": -0.20080594382714848, "mode_PIECEWISE": -0.04755171103421909, "prefill_fraction": -0.2043665285851284, "scheduled_tokens": -0.19254510985844397 }, "valid": true }, "shares": { "attention": 0.3066236078963298, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0016715827167837374, "moe_gemm": 0.6421673334694945, "moe_router": 0.010874019669713833, "norm_elementwise": 0.030945201749466352, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 996.7139999999991, "name": "triton_poi_fused_3" }, { "duration_us": 703.9869999999992, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 606.911, "name": "triton_red_fused_2" }, { "duration_us": 24.991999999999997, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 21.758999999999997, "name": "triton_poi_fused_2" }, { "duration_us": 13.247, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 13.184, "name": "triton_red_fused_1" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783849956178681726.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.34678283359255974, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9928295517926563, "mode_shares": { "FULL": { "attention": 0.34678283359255974, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0015432330235483139, "moe_gemm": 0.6057013640578384, "moe_router": 0.010146306602355423, "norm_elementwise": 0.028655814516354454, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.0071704482073436755, "representativeness": { "smd": { "decode_batch_size": 0.20138501290112165, "mode_FULL": 0.20658265838024312, "mode_NONE": -0.20080594382714848, "mode_PIECEWISE": -0.04755171103421909, "prefill_fraction": -0.2043665285851284, "scheduled_tokens": -0.19254510985844397 }, "valid": true }, "shares": { "attention": 0.34678283359255974, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0015432330235483139, "moe_gemm": 0.6057013640578384, "moe_router": 0.010146306602355423, "norm_elementwise": 0.028655814516354454, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1013.8929999999987, "name": "triton_poi_fused_3" }, { "duration_us": 711.0099999999981, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 613.2400000000005, "name": "triton_red_fused_2" }, { "duration_us": 25.055, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 22.112, "name": "triton_poi_fused_2" }, { "duration_us": 14.049, "name": "triton_red_fused_1" }, { "duration_us": 13.855, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783849993946669416.pt.trace.json.gz" } ], "P03-C00-moderate": [ { "attention_subshares": { "attention_decode": 0.23677440452100923, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9773142909813943, "mode_shares": { "FULL": { "attention": 0.23677440452100923, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.007300880477096696, "moe_gemm": 0.5916730425467414, "moe_router": 0.030667589074404745, "norm_elementwise": 0.11089837436214241, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.022685709018605626, "representativeness": { "smd": { "decode_batch_size": 3.72009366381467, "mode_FULL": 0.27793577928319474, "mode_NONE": -0.27793577928319446, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.1868864933066391, "scheduled_tokens": -0.182101722961305 }, "valid": false }, "shares": { "attention": 0.23677440452100923, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.007300880477096696, "moe_gemm": 0.5916730425467414, "moe_router": 0.030667589074404745, "norm_elementwise": 0.11089837436214241, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 576.23, "name": "triton_poi_fused_3" }, { "duration_us": 464.7449999999998, "name": "triton_red_fused_2" }, { "duration_us": 19.744, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 12.575, "name": "triton_poi_fused_2" }, { "duration_us": 11.040999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 9.41, "name": "triton_red_fused_1" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783849465841450297.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.2295917342415148, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9711974069819732, "mode_shares": { "FULL": { "attention": 0.2295917342415148, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.009291871432449663, "moe_gemm": 0.5573510710995793, "moe_router": 0.04015146373050413, "norm_elementwise": 0.13481126647792535, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.02880259301802682, "representativeness": { "smd": { "decode_batch_size": -0.27750213252727524, "mode_FULL": 0.27793577928319474, "mode_NONE": -0.27793577928319446, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.1868864933066391, "scheduled_tokens": -0.1838557206293655 }, "valid": false }, "shares": { "attention": 0.2295917342415148, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.009291871432449663, "moe_gemm": 0.5573510710995793, "moe_router": 0.04015146373050413, "norm_elementwise": 0.13481126647792535, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 571.9689999999993, "name": "triton_poi_fused_3" }, { "duration_us": 469.85699999999855, "name": "triton_red_fused_2" }, { "duration_us": 18.529, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 12.383, "name": "triton_poi_fused_2" }, { "duration_us": 9.761000000000001, "name": "triton_red_fused_1" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783849497248548609.pt.trace.json.gz" } ], "P03-C00-saturation": [ { "attention_subshares": { "attention_decode": 0.15040135314337208, "attention_mixed": 0.28933706610779675, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9918450008730845, "mode_shares": { "FULL": { "attention": 0.6859966420485143, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0019314646391670124, "moe_gemm": 0.2659878061842072, "moe_router": 0.012555897863413516, "norm_elementwise": 0.025494810657793975, "sampler": 0.0 }, "NONE": { "attention": 0.3425246256579563, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6147373284349258, "moe_router": 0.003205686402689487, "norm_elementwise": 0.030942924035345834, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.61102927558752, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0013975676747442667, "moe_gemm": 0.3571425323248457, "moe_router": 0.006697455630309823, "norm_elementwise": 0.018973805351208753, "sampler": 0.0 } }, "mode_steps": { "FULL": 6, "NONE": 1, "PIECEWISE": 1 }, "other_share": 0.008154999126915493, "representativeness": { "smd": { "decode_batch_size": 1.22313193325346, "mode_FULL": 0.7720860330486908, "mode_NONE": -1.155709946053278, "mode_PIECEWISE": 0.5, "prefill_fraction": -0.8564873113454512, "scheduled_tokens": -1.021286605051562 }, "valid": false }, "shares": { "attention": 0.4397384192511688, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.000537501805597198, "moe_gemm": 0.5172566828279285, "moe_router": 0.0055405928130157975, "norm_elementwise": 0.028771804175374255, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 2966.5110000000122, "name": "triton_poi_fused_3" }, { "duration_us": 1605.9449999999956, "name": "triton_red_fused_2" }, { "duration_us": 1552.6929999999936, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 63.32699999999999, "name": "triton_poi_fused_2" }, { "duration_us": 34.559000000000005, "name": "triton_red_fused_1" }, { "duration_us": 28.895999999999994, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 11.679, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783848741144884870.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.3425145548872434, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9914119224463182, "mode_shares": { "NONE": { "attention": 0.3425145548872434, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6147853532198007, "moe_router": 0.0032173993050482958, "norm_elementwise": 0.030894615034225702, "sampler": 0.0 } }, "mode_steps": { "NONE": 8 }, "other_share": 0.008588077553681895, "representativeness": { "smd": { "decode_batch_size": -1.5373920998057986, "mode_FULL": -1.1124192104801658, "mode_NONE": 1.1124192104801658, "mode_PIECEWISE": 0.0, "prefill_fraction": 1.1145676479021394, "scheduled_tokens": 1.1485324061566928 }, "valid": false }, "shares": { "attention": 0.3425145548872434, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6147853532198007, "moe_router": 0.0032173993050482958, "norm_elementwise": 0.030894615034225702, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 17168.532999999996, "name": "triton_poi_fused_3" }, { "duration_us": 8516.018999999993, "name": "triton_red_fused_2" }, { "duration_us": 7858.939000000003, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 365.792, "name": "triton_poi_fused_2" }, { "duration_us": 181.474, "name": "triton_red_fused_1" }, { "duration_us": 107.04, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 12.894999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783848782480504538.pt.trace.json.gz" } ], "P03-C01-moderate": [ { "attention_subshares": { "attention_decode": 0.2472611589117568, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9711954941240638, "mode_shares": { "FULL": { "attention": 0.2472611589117568, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.008981204160230193, "moe_gemm": 0.5449779176549342, "moe_router": 0.03864212767674718, "norm_elementwise": 0.13133308572039554, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.028804505875936144, "representativeness": { "smd": { "decode_batch_size": 0.12761411907604883, "mode_FULL": 0.40277438708242275, "mode_NONE": -0.39239725725147123, "mode_PIECEWISE": -0.08433231534384081, "prefill_fraction": -0.3360840189860844, "scheduled_tokens": -0.3186082852329951 }, "valid": false }, "shares": { "attention": 0.2472611589117568, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.008981204160230193, "moe_gemm": 0.5449779176549342, "moe_router": 0.03864212767674718, "norm_elementwise": 0.13133308572039554, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 608.2109999999999, "name": "triton_poi_fused_3" }, { "duration_us": 459.13399999999984, "name": "triton_red_fused_2" }, { "duration_us": 18.080000000000002, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 12.448999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 9.886, "name": "triton_red_fused_1" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783838881774721247.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.030493797355859827, "attention_mixed": 0.0, "attention_prefill": 0.2337756657652817 }, "classifiable_fraction": 0.9876621178230831, "mode_shares": { "FULL": { "attention": 0.20796901066629175, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.00949416034152379, "moe_gemm": 0.5730563859384595, "moe_router": 0.04094999186682201, "norm_elementwise": 0.138651777663304, "sampler": 0.0 }, "NONE": { "attention": 0.2847935541112115, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6698501096001059, "moe_router": 0.004797173211359188, "norm_elementwise": 0.031704685814038104, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.19039146853788674, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003165041910063069, "moe_gemm": 0.7266700356495558, "moe_router": 0.021201509715176935, "norm_elementwise": 0.04563231947124987, "sampler": 0.0 } }, "mode_steps": { "FULL": 6, "NONE": 1, "PIECEWISE": 1 }, "other_share": 0.012337882176916845, "representativeness": { "smd": { "decode_batch_size": -0.5656913025413245, "mode_FULL": -0.4645415813164409, "mode_NONE": 0.17296137292420416, "mode_PIECEWISE": 0.47910292145473704, "prefill_fraction": 0.5401368889615827, "scheduled_tokens": 0.29654274109388945 }, "valid": false }, "shares": { "attention": 0.2642694631211415, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001702544587935503, "moe_gemm": 0.6612308364176214, "moe_router": 0.011707182831279314, "norm_elementwise": 0.04875209086510538, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1139.9199999999971, "name": "triton_poi_fused_3" }, { "duration_us": 713.7360000000015, "name": "triton_red_fused_2" }, { "duration_us": 380.48100000000034, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 24.064000000000007, "name": "triton_poi_fused_2" }, { "duration_us": 20.0, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 15.997999999999998, "name": "triton_red_fused_1" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783838913535208997.pt.trace.json.gz" } ], "P03-C01-saturation": [ { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.3625175101430537, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9921751035942372, "mode_shares": { "NONE": { "attention": 0.3625175101430537, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.5972917860703632, "moe_router": 0.004233348375179386, "norm_elementwise": 0.028132459005640997, "sampler": 0.0 } }, "mode_steps": { "NONE": 8 }, "other_share": 0.007824896405762824, "representativeness": { "smd": { "decode_batch_size": 0.03842752249272106, "mode_FULL": 0.0, "mode_NONE": 0.0, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.03842752249261314, "scheduled_tokens": 0.0 }, "valid": true }, "shares": { "attention": 0.3625175101430537, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.5972917860703632, "moe_router": 0.004233348375179386, "norm_elementwise": 0.028132459005640997, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 4829.081000000003, "name": "triton_poi_fused_3" }, { "duration_us": 2461.234000000001, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 2440.887999999998, "name": "triton_red_fused_2" }, { "duration_us": 103.19999999999999, "name": "triton_poi_fused_2" }, { "duration_us": 54.239, "name": "triton_red_fused_1" }, { "duration_us": 34.912000000000006, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 10.815999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783838155509202718.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.3233680934686369, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9917064998087011, "mode_shares": { "NONE": { "attention": 0.3233680934686369, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6340271091943758, "moe_router": 0.004488327860901843, "norm_elementwise": 0.029822969284786536, "sampler": 0.0 } }, "mode_steps": { "NONE": 8 }, "other_share": 0.008293500191298969, "representativeness": { "smd": { "decode_batch_size": 0.03842752249272106, "mode_FULL": 0.0, "mode_NONE": 0.0, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.03842752249261314, "scheduled_tokens": 0.0 }, "valid": true }, "shares": { "attention": 0.3233680934686369, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6340271091943758, "moe_router": 0.004488327860901843, "norm_elementwise": 0.029822969284786536, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 4825.282999999999, "name": "triton_poi_fused_3" }, { "duration_us": 2464.268999999999, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 2440.0180000000014, "name": "triton_red_fused_2" }, { "duration_us": 103.362, "name": "triton_poi_fused_2" }, { "duration_us": 54.37, "name": "triton_red_fused_1" }, { "duration_us": 34.081, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 11.167, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783838204169798936.pt.trace.json.gz" } ], "P03-C10-moderate": [ { "attention_subshares": { "attention_decode": 0.22514759732195092, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9713506698327266, "mode_shares": { "FULL": { "attention": 0.22514759732195092, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.009442025728651632, "moe_gemm": 0.5602617147563997, "moe_router": 0.03949200310681736, "norm_elementwise": 0.13700732891890693, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.02864933016727339, "representativeness": { "smd": { "decode_batch_size": -0.18984540767127392, "mode_FULL": 0.2782013992817753, "mode_NONE": -0.27820139928177545, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.18350522021486032, "scheduled_tokens": -0.18063803827124955 }, "valid": false }, "shares": { "attention": 0.22514759732195092, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.009442025728651632, "moe_gemm": 0.5602617147563997, "moe_router": 0.03949200310681736, "norm_elementwise": 0.13700732891890693, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 581.8899999999993, "name": "triton_poi_fused_3" }, { "duration_us": 449.5400000000006, "name": "triton_red_fused_2" }, { "duration_us": 18.656, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.120999999999999, "name": "triton_poi_fused_2" }, { "duration_us": 9.725999999999999, "name": "triton_red_fused_1" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783836530738313739.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.22556467485036294, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9704584620048622, "mode_shares": { "FULL": { "attention": 0.22556467485036294, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.009411480644856082, "moe_gemm": 0.5591648344398723, "moe_router": 0.03945587906666355, "norm_elementwise": 0.13686159300310727, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.02954153799513786, "representativeness": { "smd": { "decode_batch_size": -0.18984540767127392, "mode_FULL": 0.2782013992817753, "mode_NONE": -0.27820139928177545, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.18350522021486032, "scheduled_tokens": -0.18063803827124955 }, "valid": false }, "shares": { "attention": 0.22556467485036294, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.009411480644856082, "moe_gemm": 0.5591648344398723, "moe_router": 0.03945587906666355, "norm_elementwise": 0.13686159300310727, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 616.4500000000008, "name": "triton_poi_fused_3" }, { "duration_us": 449.8830000000004, "name": "triton_red_fused_2" }, { "duration_us": 19.168, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.6, "name": "triton_poi_fused_2" }, { "duration_us": 9.630999999999998, "name": "triton_red_fused_1" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783836562201333740.pt.trace.json.gz" } ], "P04-C00-moderate": [ { "attention_subshares": { "attention_decode": 0.45337846230845036, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9811078968569179, "mode_shares": { "FULL": { "attention": 0.45337846230845036, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.00447249169315189, "moe_gemm": 0.4320822710822647, "moe_router": 0.03260980879841117, "norm_elementwise": 0.05856486297463963, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.01889210314308214, "representativeness": { "smd": { "decode_batch_size": 0.20844725339793926, "mode_FULL": 0.18226661968758462, "mode_NONE": -0.18226661968758412, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.15943564286260098, "scheduled_tokens": -0.15585724120282418 }, "valid": true }, "shares": { "attention": 0.45337846230845036, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.00447249169315189, "moe_gemm": 0.4320822710822647, "moe_router": 0.03260980879841117, "norm_elementwise": 0.05856486297463963, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 600.4589999999997, "name": "triton_poi_fused_3" }, { "duration_us": 503.8849999999992, "name": "triton_red_fused_2" }, { "duration_us": 467.6160000000004, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 19.391000000000002, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 12.958999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 11.197999999999999, "name": "triton_red_fused_1" }, { "duration_us": 9.726999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783849465791477789.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.5042949115154224, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.980970138873411, "mode_shares": { "FULL": { "attention": 0.5042949115154224, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004490478325551558, "moe_gemm": 0.3806685401425692, "moe_router": 0.032988086256013634, "norm_elementwise": 0.058528122633854276, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.019029861126589043, "representativeness": { "smd": { "decode_batch_size": 0.20844725339793926, "mode_FULL": 0.18226661968758462, "mode_NONE": -0.18226661968758412, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.15943564286260098, "scheduled_tokens": -0.15585724120282418 }, "valid": true }, "shares": { "attention": 0.5042949115154224, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004490478325551558, "moe_gemm": 0.3806685401425692, "moe_router": 0.032988086256013634, "norm_elementwise": 0.058528122633854276, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 600.0620000000005, "name": "triton_poi_fused_3" }, { "duration_us": 501.89399999999864, "name": "triton_red_fused_2" }, { "duration_us": 467.97200000000095, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 19.328, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 12.800999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 11.870999999999999, "name": "triton_red_fused_1" }, { "duration_us": 10.014999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783849497082189253.pt.trace.json.gz" } ], "P04-C00-saturation": [ { "attention_subshares": { "attention_decode": 0.6545383651006825, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.992872517456777, "mode_shares": { "FULL": { "attention": 0.6545383651006825, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001725224109977307, "moe_gemm": 0.30244289390345225, "moe_router": 0.011446277854389742, "norm_elementwise": 0.022719756488275074, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.007127482543223056, "representativeness": { "smd": { "decode_batch_size": -2.090753569627607, "mode_FULL": 0.3444176950404237, "mode_NONE": -0.3444176950404235, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.3279408074303144, "scheduled_tokens": -0.3384806476596461 }, "valid": false }, "shares": { "attention": 0.6545383651006825, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001725224109977307, "moe_gemm": 0.30244289390345225, "moe_router": 0.011446277854389742, "norm_elementwise": 0.022719756488275074, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 702.7299999999998, "name": "triton_poi_fused_3" }, { "duration_us": 538.8529999999995, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 511.6859999999996, "name": "triton_red_fused_2" }, { "duration_us": 20.480999999999998, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.599, "name": "triton_poi_fused_2" }, { "duration_us": 11.903999999999998, "name": "triton_red_fused_1" }, { "duration_us": 10.879999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783848739183825698.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.6629935506677639, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9927205146123725, "mode_shares": { "FULL": { "attention": 0.6629935506677639, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0017655694129604385, "moe_gemm": 0.29304677622038244, "moe_router": 0.01168833427441094, "norm_elementwise": 0.02322628403685483, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.007279485387627501, "representativeness": { "smd": { "decode_batch_size": -3.0407898355557177, "mode_FULL": 0.3444176950404237, "mode_NONE": -0.3444176950404235, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.3279408074303144, "scheduled_tokens": -0.3392815338864717 }, "valid": false }, "shares": { "attention": 0.6629935506677639, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0017655694129604385, "moe_gemm": 0.29304677622038244, "moe_router": 0.01168833427441094, "norm_elementwise": 0.02322628403685483, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 697.0249999999994, "name": "triton_poi_fused_3" }, { "duration_us": 539.4639999999994, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 512.0369999999991, "name": "triton_red_fused_2" }, { "duration_us": 20.703, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.440999999999999, "name": "triton_poi_fused_2" }, { "duration_us": 11.392999999999999, "name": "triton_red_fused_1" }, { "duration_us": 11.231999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783848772357502908.pt.trace.json.gz" } ], "P06-C00-moderate": [ { "attention_subshares": { "attention_decode": 0.2490290455613554, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9782676099166654, "mode_shares": { "FULL": { "attention": 0.2490290455613554, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.005145523506508112, "moe_gemm": 0.6200403635488907, "moe_router": 0.03550127037050399, "norm_elementwise": 0.06855140692940716, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.021732390083334552, "representativeness": { "smd": { "decode_batch_size": -0.7216535064826213, "mode_FULL": 0.13539969781837916, "mode_NONE": -0.1341287527105229, "mode_PIECEWISE": -0.018343220956176326, "prefill_fraction": -0.13284443594178524, "scheduled_tokens": -0.12475886497271786 }, "valid": false }, "shares": { "attention": 0.2490290455613554, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.005145523506508112, "moe_gemm": 0.6200403635488907, "moe_router": 0.03550127037050399, "norm_elementwise": 0.06855140692940716, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 597.553, "name": "triton_poi_fused_3" }, { "duration_us": 503.07699999999915, "name": "triton_red_fused_2" }, { "duration_us": 466.9400000000012, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 19.869999999999997, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.854, "name": "triton_poi_fused_2" }, { "duration_us": 11.744, "name": "triton_red_fused_1" }, { "duration_us": 9.727, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783850544482514161.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.382897364177646, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9857570160520932, "mode_shares": { "FULL": { "attention": 0.382897364177646, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003409296822253497, "moe_gemm": 0.5303535709645394, "moe_router": 0.023879803771651553, "norm_elementwise": 0.04521698031600275, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.014242983947906827, "representativeness": { "smd": { "decode_batch_size": 2.7828468550637027, "mode_FULL": 0.13539969781837916, "mode_NONE": -0.1341287527105229, "mode_PIECEWISE": -0.018343220956176326, "prefill_fraction": -0.13284443594178524, "scheduled_tokens": -0.10682572566427663 }, "valid": false }, "shares": { "attention": 0.382897364177646, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003409296822253497, "moe_gemm": 0.5303535709645394, "moe_router": 0.023879803771651553, "norm_elementwise": 0.04521698031600275, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 620.7480000000002, "name": "triton_poi_fused_3" }, { "duration_us": 515.2009999999995, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 493.54399999999913, "name": "triton_red_fused_2" }, { "duration_us": 19.936, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.312, "name": "triton_poi_fused_2" }, { "duration_us": 10.751999999999999, "name": "triton_red_fused_1" }, { "duration_us": 10.4, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783850576196502468.pt.trace.json.gz" } ], "P06-C00-saturation": [ { "attention_subshares": { "attention_decode": 0.5606386878931048, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9937049249586525, "mode_shares": { "FULL": { "attention": 0.5606386878931048, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0015728835856848925, "moe_gemm": 0.3985345690982096, "moe_router": 0.010374903112678729, "norm_elementwise": 0.022583881268974364, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.006295075041347565, "representativeness": { "smd": { "decode_batch_size": -0.19939502094061695, "mode_FULL": 0.3784962133407253, "mode_NONE": -0.3784962133407256, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.34967744618584184, "scheduled_tokens": -0.3730920628084988 }, "valid": false }, "shares": { "attention": 0.5606386878931048, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0015728835856848925, "moe_gemm": 0.3985345690982096, "moe_router": 0.010374903112678729, "norm_elementwise": 0.022583881268974364, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 730.718, "name": "triton_poi_fused_3" }, { "duration_us": 532.1659999999997, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 517.7589999999993, "name": "triton_red_fused_2" }, { "duration_us": 22.624, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 14.944999999999999, "name": "triton_poi_fused_2" }, { "duration_us": 12.351999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 11.359999999999998, "name": "triton_red_fused_1" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783849955632275097.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.5711221921286438, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9938941650105397, "mode_shares": { "FULL": { "attention": 0.5711221921286438, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001510179204207269, "moe_gemm": 0.3884028034591522, "moe_router": 0.010456005468211384, "norm_elementwise": 0.022402984750325126, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.006105834989460318, "representativeness": { "smd": { "decode_batch_size": -3.0651651743014807, "mode_FULL": 0.3784962133407253, "mode_NONE": -0.3784962133407256, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.34967744618584184, "scheduled_tokens": -0.381504751465261 }, "valid": false }, "shares": { "attention": 0.5711221921286438, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001510179204207269, "moe_gemm": 0.3884028034591522, "moe_router": 0.010456005468211384, "norm_elementwise": 0.022402984750325126, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 735.0089999999993, "name": "triton_poi_fused_3" }, { "duration_us": 530.0759999999996, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 511.90599999999927, "name": "triton_red_fused_2" }, { "duration_us": 21.855999999999995, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 15.872, "name": "triton_poi_fused_2" }, { "duration_us": 11.360999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 10.878999999999998, "name": "triton_red_fused_1" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783849989625437379.pt.trace.json.gz" } ], "P06-C01-moderate": [ { "attention_subshares": { "attention_decode": 0.016563491820063184, "attention_mixed": 0.3001356839582549, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9913361171706583, "mode_shares": { "FULL": { "attention": 0.3160414926288235, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0038264604478624375, "moe_gemm": 0.5878127540909809, "moe_router": 0.025157477959619073, "norm_elementwise": 0.05121416016089138, "sampler": 0.0 }, "NONE": { "attention": 0.31673555083570937, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6406959135573278, "moe_router": 0.004599858882822663, "norm_elementwise": 0.029707643839264736, "sampler": 0.0 } }, "mode_steps": { "FULL": 3, "NONE": 5 }, "other_share": 0.008663882829341732, "representativeness": { "smd": { "decode_batch_size": 1.2368003091321618, "mode_FULL": -1.5398684829814582, "mode_NONE": 1.543433248193871, "mode_PIECEWISE": -0.03766886010245595, "prefill_fraction": 1.5423098869457519, "scheduled_tokens": 1.5062889639493047 }, "valid": false }, "shares": { "attention": 0.3166991757783181, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.00020054185227634405, "moe_gemm": 0.637924347798813, "moe_router": 0.00567726790461336, "norm_elementwise": 0.03083478383663744, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 3051.4100000000076, "name": "triton_poi_fused_3" }, { "duration_us": 1636.7499999999984, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 1627.5970000000007, "name": "triton_red_fused_2" }, { "duration_us": 65.154, "name": "triton_poi_fused_2" }, { "duration_us": 36.064, "name": "triton_red_fused_1" }, { "duration_us": 24.608, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 10.561, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783848264687091429.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.37214450648638964, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9883428882887048, "mode_shares": { "FULL": { "attention": 0.37214450648638964, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.00282500541869895, "moe_gemm": 0.5573743342631299, "moe_router": 0.017973887722641455, "norm_elementwise": 0.038025154397844804, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.01165711171129528, "representativeness": { "smd": { "decode_batch_size": 3.172928254461621, "mode_FULL": 0.25227637804266817, "mode_NONE": -0.2492686165020934, "mode_PIECEWISE": -0.03766886010245595, "prefill_fraction": -0.25064540002066804, "scheduled_tokens": -0.20625098090671584 }, "valid": false }, "shares": { "attention": 0.37214450648638964, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.00282500541869895, "moe_gemm": 0.5573743342631299, "moe_router": 0.017973887722641455, "norm_elementwise": 0.038025154397844804, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 656.2589999999994, "name": "triton_poi_fused_3" }, { "duration_us": 496.6409999999987, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 494.02099999999876, "name": "triton_red_fused_2" }, { "duration_us": 19.584, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 14.175999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 11.678999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 10.911999999999999, "name": "triton_red_fused_1" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783848304448588625.pt.trace.json.gz" } ], "P06-C01-saturation": [ { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.3895842363152871, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9927290912532949, "mode_shares": { "NONE": { "attention": 0.3895842363152871, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.5731444916792802, "moe_router": 0.003933173990421752, "norm_elementwise": 0.026067189268305868, "sampler": 0.0 } }, "mode_steps": { "NONE": 8 }, "other_share": 0.007270908746705119, "representativeness": { "smd": { "decode_batch_size": -0.4361011161328784, "mode_FULL": -2.2231293099337295, "mode_NONE": 2.2283091632883223, "mode_PIECEWISE": -0.043664375559957246, "prefill_fraction": 2.341843613561519, "scheduled_tokens": 2.2566609549134715 }, "valid": false }, "shares": { "attention": 0.3895842363152871, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.5731444916792802, "moe_router": 0.003933173990421752, "norm_elementwise": 0.026067189268305868, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 4807.593000000002, "name": "triton_poi_fused_3" }, { "duration_us": 2442.074, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 2441.511, "name": "triton_red_fused_2" }, { "duration_us": 102.624, "name": "triton_poi_fused_2" }, { "duration_us": 53.760999999999996, "name": "triton_red_fused_1" }, { "duration_us": 36.193, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 11.647999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783847493627203394.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.3945011262454341, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9927395420899131, "mode_shares": { "NONE": { "attention": 0.3945011262454341, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.5682708789371121, "moe_router": 0.003929026668942022, "norm_elementwise": 0.02603851023842481, "sampler": 0.0 } }, "mode_steps": { "NONE": 8 }, "other_share": 0.007260457910086926, "representativeness": { "smd": { "decode_batch_size": -3.1519864341790544, "mode_FULL": -2.2231293099337295, "mode_NONE": 2.2283091632883223, "mode_PIECEWISE": -0.043664375559957246, "prefill_fraction": 2.366260389350378, "scheduled_tokens": 2.2566609549134715 }, "valid": false }, "shares": { "attention": 0.3945011262454341, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.5682708789371121, "moe_router": 0.003929026668942022, "norm_elementwise": 0.02603851023842481, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 4813.921000000002, "name": "triton_poi_fused_3" }, { "duration_us": 2446.1619999999994, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 2437.272, "name": "triton_red_fused_2" }, { "duration_us": 102.78399999999999, "name": "triton_poi_fused_2" }, { "duration_us": 54.273, "name": "triton_red_fused_1" }, { "duration_us": 35.68, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 11.008, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783847543255284600.pt.trace.json.gz" } ], "P06-C10-moderate": [ { "attention_subshares": { "attention_decode": 0.3581687545191966, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9772718952687278, "mode_shares": { "FULL": { "attention": 0.3581687545191966, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.00525419312260622, "moe_gemm": 0.5105179315671342, "moe_router": 0.03567192120640712, "norm_elementwise": 0.06765909485338374, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.022728104731272125, "representativeness": { "smd": { "decode_batch_size": -0.9404968816184628, "mode_FULL": 0.1374340854376679, "mode_NONE": -0.1374340854376676, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.13478349167720893, "scheduled_tokens": -0.1290275248369585 }, "valid": false }, "shares": { "attention": 0.3581687545191966, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.00525419312260622, "moe_gemm": 0.5105179315671342, "moe_router": 0.03567192120640712, "norm_elementwise": 0.06765909485338374, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 630.1189999999997, "name": "triton_poi_fused_3" }, { "duration_us": 521.6069999999993, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 499.6179999999991, "name": "triton_red_fused_2" }, { "duration_us": 19.392, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.6, "name": "triton_poi_fused_2" }, { "duration_us": 10.881, "name": "triton_red_fused_1" }, { "duration_us": 9.631, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783850544481880252.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.417531453105595, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9841451093044552, "mode_shares": { "FULL": { "attention": 0.417531453105595, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0038280359471430728, "moe_gemm": 0.48769062887878234, "moe_router": 0.024961428483772106, "norm_elementwise": 0.050133562889162694, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.015854890695544816, "representativeness": { "smd": { "decode_batch_size": 2.1353453919214704, "mode_FULL": 0.1374340854376679, "mode_NONE": -0.1374340854376676, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.13478349167720893, "scheduled_tokens": -0.11208567974807711 }, "valid": false }, "shares": { "attention": 0.417531453105595, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0038280359471430728, "moe_gemm": 0.48769062887878234, "moe_router": 0.024961428483772106, "norm_elementwise": 0.050133562889162694, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 633.0599999999998, "name": "triton_poi_fused_3" }, { "duration_us": 495.7439999999989, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 490.0149999999992, "name": "triton_red_fused_2" }, { "duration_us": 19.04, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.791999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 10.882, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 10.047, "name": "triton_red_fused_1" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783850575822210846.pt.trace.json.gz" } ], "P06-C10-saturation": [ { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.3486689259270977, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9915388739029576, "mode_shares": { "NONE": { "attention": 0.3486689259270977, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6093714248402938, "moe_router": 0.003167635514417327, "norm_elementwise": 0.030330887621148654, "sampler": 0.0 } }, "mode_steps": { "NONE": 8 }, "other_share": 0.008461126097042464, "representativeness": { "smd": { "decode_batch_size": -6.093102704587387, "mode_FULL": -5.409862359976508, "mode_NONE": 5.409862359976508, "mode_PIECEWISE": 0.0, "prefill_fraction": 5.577249352958417, "scheduled_tokens": 6.977467251638274 }, "valid": false }, "shares": { "attention": 0.3486689259270977, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6093714248402938, "moe_router": 0.003167635514417327, "norm_elementwise": 0.030330887621148654, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 18628.55999999999, "name": "triton_poi_fused_3" }, { "duration_us": 9220.226999999993, "name": "triton_red_fused_2" }, { "duration_us": 8416.866999999997, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 397.24800000000005, "name": "triton_poi_fused_2" }, { "duration_us": 195.808, "name": "triton_red_fused_1" }, { "duration_us": 109.279, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.024, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783849962666875300.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.5719043088501389, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9916731652872516, "mode_shares": { "FULL": { "attention": 0.5719043088501389, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.002016827326928409, "moe_gemm": 0.37609168384078084, "moe_router": 0.013852953759290538, "norm_elementwise": 0.02780739151011282, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.008326834712748461, "representativeness": { "smd": { "decode_batch_size": 0.34266016260318394, "mode_FULL": 0.36945401482766393, "mode_NONE": -0.36945401482766393, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.36861766414224534, "scheduled_tokens": -0.3264149440726429 }, "valid": false }, "shares": { "attention": 0.5719043088501389, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.002016827326928409, "moe_gemm": 0.37609168384078084, "moe_router": 0.013852953759290538, "norm_elementwise": 0.02780739151011282, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 694.7229999999995, "name": "triton_poi_fused_3" }, { "duration_us": 546.8509999999995, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 520.2939999999993, "name": "triton_red_fused_2" }, { "duration_us": 20.320999999999998, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 14.463, "name": "triton_poi_fused_2" }, { "duration_us": 12.448999999999998, "name": "triton_red_fused_1" }, { "duration_us": 10.783999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783850011262475600.pt.trace.json.gz" } ], "P06-C11-moderate": [ { "attention_subshares": { "attention_decode": 0.31298009715328673, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9837880586014649, "mode_shares": { "FULL": { "attention": 0.31298009715328673, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004023145886862297, "moe_gemm": 0.5886224548783123, "moe_router": 0.026592515275261283, "norm_elementwise": 0.051569845407742246, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.01621194139853512, "representativeness": { "smd": { "decode_batch_size": 2.2622779907056527, "mode_FULL": 0.2570884920608091, "mode_NONE": -0.25558416463536143, "mode_PIECEWISE": -0.026892314000411845, "prefill_fraction": -0.2554724535338412, "scheduled_tokens": -0.22611835970475505 }, "valid": false }, "shares": { "attention": 0.31298009715328673, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004023145886862297, "moe_gemm": 0.5886224548783123, "moe_router": 0.026592515275261283, "norm_elementwise": 0.051569845407742246, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 633.8630000000002, "name": "triton_poi_fused_3" }, { "duration_us": 494.91799999999904, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 492.54099999999926, "name": "triton_red_fused_2" }, { "duration_us": 19.038999999999998, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.568, "name": "triton_poi_fused_2" }, { "duration_us": 11.584, "name": "triton_red_fused_1" }, { "duration_us": 10.719999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783850544703259931.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.285815805689067, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9795145559108047, "mode_shares": { "FULL": { "attention": 0.285815805689067, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004890634397475269, "moe_gemm": 0.594753338701119, "moe_router": 0.03200944848645275, "norm_elementwise": 0.062045328636690614, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.020485444089195285, "representativeness": { "smd": { "decode_batch_size": -0.9097707612085933, "mode_FULL": 0.2570884920608091, "mode_NONE": -0.25558416463536143, "mode_PIECEWISE": -0.026892314000411845, "prefill_fraction": -0.2554724535338412, "scheduled_tokens": -0.2591423482439635 }, "valid": false }, "shares": { "attention": 0.285815805689067, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004890634397475269, "moe_gemm": 0.594753338701119, "moe_router": 0.03200944848645275, "norm_elementwise": 0.062045328636690614, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 616.3130000000001, "name": "triton_poi_fused_3" }, { "duration_us": 518.4359999999996, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 500.8009999999993, "name": "triton_red_fused_2" }, { "duration_us": 18.976999999999997, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 12.831999999999999, "name": "triton_poi_fused_2" }, { "duration_us": 11.774999999999999, "name": "triton_red_fused_1" }, { "duration_us": 10.142999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783850576213406484.pt.trace.json.gz" } ], "P06-C11-saturation": [ { "attention_subshares": { "attention_decode": 0.5565323350091496, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9922271393697571, "mode_shares": { "FULL": { "attention": 0.5565323350091496, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0019180859437863745, "moe_gemm": 0.39491275272816917, "moe_router": 0.012754982760746365, "norm_elementwise": 0.026108982927905665, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.0077728606302428565, "representativeness": { "smd": { "decode_batch_size": 0.722221197086119, "mode_FULL": 0.7873442980499663, "mode_NONE": -0.7857620597700242, "mode_PIECEWISE": -0.038110796698335295, "prefill_fraction": -0.7857531825398673, "scheduled_tokens": -0.7401743374164678 }, "valid": false }, "shares": { "attention": 0.5565323350091496, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0019180859437863745, "moe_gemm": 0.39491275272816917, "moe_router": 0.012754982760746365, "norm_elementwise": 0.026108982927905665, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 699.4259999999995, "name": "triton_poi_fused_3" }, { "duration_us": 542.1849999999998, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 520.0949999999991, "name": "triton_red_fused_2" }, { "duration_us": 21.345000000000002, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.728, "name": "triton_poi_fused_2" }, { "duration_us": 11.902999999999999, "name": "triton_red_fused_1" }, { "duration_us": 10.945, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783849955389093025.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.5577097612622229, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9919246666563806, "mode_shares": { "FULL": { "attention": 0.5577097612622229, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001982724387439752, "moe_gemm": 0.3920744686718595, "moe_router": 0.013242542857418157, "norm_elementwise": 0.026915169477440156, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.008075333343619472, "representativeness": { "smd": { "decode_batch_size": 0.722221197086119, "mode_FULL": 0.7873442980499663, "mode_NONE": -0.7857620597700242, "mode_PIECEWISE": -0.038110796698335295, "prefill_fraction": -0.7857531825398673, "scheduled_tokens": -0.7401743374164678 }, "valid": false }, "shares": { "attention": 0.5577097612622229, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001982724387439752, "moe_gemm": 0.3920744686718595, "moe_router": 0.013242542857418157, "norm_elementwise": 0.026915169477440156, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 705.1269999999993, "name": "triton_poi_fused_3" }, { "duration_us": 544.0159999999997, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 521.0479999999991, "name": "triton_red_fused_2" }, { "duration_us": 21.279999999999998, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.824, "name": "triton_poi_fused_2" }, { "duration_us": 12.191999999999998, "name": "triton_red_fused_1" }, { "duration_us": 11.200999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783849988477975368.pt.trace.json.gz" } ], "P07-C00-moderate": [ { "attention_subshares": { "attention_decode": 0.306761436001029, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9841089106220091, "mode_shares": { "FULL": { "attention": 0.306761436001029, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003944802403864725, "moe_gemm": 0.5964090291561805, "moe_router": 0.02562456323133302, "norm_elementwise": 0.051369079829601885, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.015891089377990907, "representativeness": { "smd": { "decode_batch_size": -0.18368608035893982, "mode_FULL": 0.1535286967084372, "mode_NONE": -0.15352869670843752, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.1535266720575854, "scheduled_tokens": -0.13391206652423035 }, "valid": true }, "shares": { "attention": 0.306761436001029, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003944802403864725, "moe_gemm": 0.5964090291561805, "moe_router": 0.02562456323133302, "norm_elementwise": 0.051369079829601885, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 606.694, "name": "triton_poi_fused_3" }, { "duration_us": 538.9419999999992, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 496.9549999999989, "name": "triton_red_fused_2" }, { "duration_us": 20.128, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 15.04, "name": "triton_poi_fused_2" }, { "duration_us": 10.56, "name": "triton_red_fused_1" }, { "duration_us": 10.304, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783836530765988779.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.2666065580814879, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9860189886811974, "mode_shares": { "FULL": { "attention": 0.2666065580814879, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0034992714146667428, "moe_gemm": 0.6472552645315595, "moe_router": 0.02277286906470575, "norm_elementwise": 0.04588502558877749, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.013981011318802606, "representativeness": { "smd": { "decode_batch_size": 3.069910871828644, "mode_FULL": 0.1535286967084372, "mode_NONE": -0.15352869670843752, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.1535266720575854, "scheduled_tokens": -0.11608746652035899 }, "valid": false }, "shares": { "attention": 0.2666065580814879, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0034992714146667428, "moe_gemm": 0.6472552645315595, "moe_router": 0.02277286906470575, "norm_elementwise": 0.04588502558877749, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 621.5659999999995, "name": "triton_poi_fused_3" }, { "duration_us": 529.2479999999987, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 510.27699999999976, "name": "triton_red_fused_2" }, { "duration_us": 20.607000000000003, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.184, "name": "triton_poi_fused_2" }, { "duration_us": 11.230999999999998, "name": "triton_red_fused_1" }, { "duration_us": 10.817, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783836562828610579.pt.trace.json.gz" } ], "P08-C00-moderate": [ { "attention_subshares": { "attention_decode": 0.3248872069635257, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9877052895017178, "mode_shares": { "FULL": { "attention": 0.3248872069635257, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0031072028443770152, "moe_gemm": 0.5984635601986847, "moe_router": 0.020260919566213807, "norm_elementwise": 0.04098639992891659, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.012294710498282197, "representativeness": { "smd": { "decode_batch_size": 1.0901560791930118, "mode_FULL": 0.16434181266464418, "mode_NONE": -0.16434181266464443, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.16432997461824633, "scheduled_tokens": -0.1413297101061453 }, "valid": false }, "shares": { "attention": 0.3248872069635257, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0031072028443770152, "moe_gemm": 0.5984635601986847, "moe_router": 0.020260919566213807, "norm_elementwise": 0.04098639992891659, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 654.3379999999997, "name": "triton_poi_fused_3" }, { "duration_us": 552.4199999999996, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 513.1979999999996, "name": "triton_red_fused_2" }, { "duration_us": 21.089000000000002, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 14.015999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 12.127999999999998, "name": "triton_red_fused_1" }, { "duration_us": 10.719, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783836530860694701.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.3669917099645223, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9854450802968766, "mode_shares": { "FULL": { "attention": 0.3669917099645223, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003724234761488658, "moe_gemm": 0.5428235608185195, "moe_router": 0.024088695306046685, "norm_elementwise": 0.04781687944629951, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.014554919703123427, "representativeness": { "smd": { "decode_batch_size": -1.4164397504981734, "mode_FULL": 0.16434181266464418, "mode_NONE": -0.16434181266464443, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.16432997461824633, "scheduled_tokens": -0.19075947310069616 }, "valid": false }, "shares": { "attention": 0.3669917099645223, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003724234761488658, "moe_gemm": 0.5428235608185195, "moe_router": 0.024088695306046685, "norm_elementwise": 0.04781687944629951, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 632.7909999999997, "name": "triton_poi_fused_3" }, { "duration_us": 540.1919999999998, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 511.9399999999992, "name": "triton_red_fused_2" }, { "duration_us": 20.673000000000002, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.665, "name": "triton_poi_fused_2" }, { "duration_us": 11.713, "name": "triton_red_fused_1" }, { "duration_us": 10.878999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783836563379173349.pt.trace.json.gz" } ], "P09-C00-moderate": [ { "attention_subshares": { "attention_decode": 0.08835627115447606, "attention_mixed": 0.11385037570991731, "attention_prefill": 0.0 }, "classifiable_fraction": 0.988346330660954, "mode_shares": { "FULL": { "attention": 0.280249688903593, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004209638462393143, "moe_gemm": 0.6254634471394533, "moe_router": 0.02523969717175661, "norm_elementwise": 0.0493304218340256, "sampler": 0.0 }, "NONE": { "attention": 0.14806901527656063, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.7989631873012853, "moe_router": 0.006717474937844798, "norm_elementwise": 0.036240204978569675, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.18871401371634564, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0022585830433693877, "moe_gemm": 0.7546316751137306, "moe_router": 0.012749732426996046, "norm_elementwise": 0.031927806640493814, "sampler": 0.0 } }, "mode_steps": { "FULL": 5, "NONE": 1, "PIECEWISE": 2 }, "other_share": 0.011653669339046026, "representativeness": { "smd": { "decode_batch_size": 2.5579606107986748, "mode_FULL": -0.6775421426296558, "mode_NONE": 0.2503307644752007, "mode_PIECEWISE": 0.5907929693818461, "prefill_fraction": 0.6661033678566376, "scheduled_tokens": 0.05206272885676596 }, "valid": false }, "shares": { "attention": 0.20220664686439338, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.002019814379523439, "moe_gemm": 0.7306681072672004, "moe_router": 0.014406944379520907, "norm_elementwise": 0.039044817770315786, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1078.7899999999981, "name": "triton_poi_fused_3" }, { "duration_us": 718.971000000001, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 663.9299999999997, "name": "triton_red_fused_2" }, { "duration_us": 22.880000000000003, "name": "triton_poi_fused_2" }, { "duration_us": 22.017, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 14.112, "name": "triton_red_fused_1" }, { "duration_us": 10.974999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783848263375341068.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.09568605186600879, "attention_mixed": 0.025924532025613695, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9819166279177437, "mode_shares": { "FULL": { "attention": 0.14040386061386476, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.006289384167983417, "moe_gemm": 0.7278572814656825, "moe_router": 0.03517706269456804, "norm_elementwise": 0.06867748249282202, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.08139719907850929, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0022138539380632135, "moe_gemm": 0.8578037652991323, "moe_router": 0.01403539873195149, "norm_elementwise": 0.033980351851418185, "sampler": 0.0 } }, "mode_steps": { "FULL": 7, "PIECEWISE": 1 }, "other_share": 0.01808337208225627, "representativeness": { "smd": { "decode_batch_size": -0.19954189900373331, "mode_FULL": -0.10469513477046205, "mode_NONE": -0.32861907697425397, "mode_PIECEWISE": 0.29736821980293143, "prefill_fraction": 0.10420387771831544, "scheduled_tokens": -0.23288793337699637 }, "valid": false }, "shares": { "attention": 0.12161058389162249, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004991351616949132, "moe_gemm": 0.7692444768470234, "moe_router": 0.028443566325178558, "norm_elementwise": 0.05762664923697027, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 667.7419999999993, "name": "triton_poi_fused_3" }, { "duration_us": 523.011999999999, "name": "triton_red_fused_2" }, { "duration_us": 498.98300000000086, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 20.736, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 14.591, "name": "triton_poi_fused_2" }, { "duration_us": 11.645, "name": "triton_red_fused_1" }, { "duration_us": 11.36, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783848297311321503.pt.trace.json.gz" } ], "P09-C00-saturation": [ { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.24676580346741184, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9902796451206958, "mode_shares": { "NONE": { "attention": 0.24676580346741184, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.7048192593007057, "moe_router": 0.0036328436089412205, "norm_elementwise": 0.035061738743637105, "sampler": 0.0 } }, "mode_steps": { "NONE": 8 }, "other_share": 0.009720354879304175, "representativeness": { "smd": { "decode_batch_size": 1.259998751515166, "mode_FULL": -1.0890519340869804, "mode_NONE": 1.0890519340869804, "mode_PIECEWISE": 0.0, "prefill_fraction": 1.1263920173520792, "scheduled_tokens": 1.3450157218366598 }, "valid": false }, "shares": { "attention": 0.24676580346741184, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.7048192593007057, "moe_router": 0.0036328436089412205, "norm_elementwise": 0.035061738743637105, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 18507.434, "name": "triton_poi_fused_3" }, { "duration_us": 9166.28299999999, "name": "triton_red_fused_2" }, { "duration_us": 8451.682000000004, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 396.608, "name": "triton_poi_fused_2" }, { "duration_us": 195.36100000000002, "name": "triton_red_fused_1" }, { "duration_us": 75.745, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 15.616, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783847497572190687.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.27787874681050084, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9906768293176031, "mode_shares": { "NONE": { "attention": 0.27787874681050084, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6757237742248838, "moe_router": 0.0034783848147879478, "norm_elementwise": 0.03359592346743046, "sampler": 0.0 } }, "mode_steps": { "NONE": 8 }, "other_share": 0.009323170682396877, "representativeness": { "smd": { "decode_batch_size": -0.2365580579355552, "mode_FULL": -1.0890519340869804, "mode_NONE": 1.0890519340869804, "mode_PIECEWISE": 0.0, "prefill_fraction": 1.1326772391141862, "scheduled_tokens": 1.3450157218366598 }, "valid": false }, "shares": { "attention": 0.27787874681050084, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6757237742248838, "moe_router": 0.0034783848147879478, "norm_elementwise": 0.03359592346743046, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 18504.999000000003, "name": "triton_poi_fused_3" }, { "duration_us": 9192.093999999992, "name": "triton_red_fused_2" }, { "duration_us": 8458.98800000001, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 398.754, "name": "triton_poi_fused_2" }, { "duration_us": 195.68099999999998, "name": "triton_red_fused_1" }, { "duration_us": 84.479, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 15.392, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783847556128452812.pt.trace.json.gz" } ], "P10-C00-moderate": [ { "attention_subshares": { "attention_decode": 0.3087850643091725, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.985252225101006, "mode_shares": { "FULL": { "attention": 0.3087850643091725, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.005163136163815447, "moe_gemm": 0.5777999387887653, "moe_router": 0.02008575072504131, "norm_elementwise": 0.07341833511421153, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.014747774898993987, "representativeness": { "smd": { "decode_batch_size": 4.655696267017126, "mode_FULL": 0.17677689026422408, "mode_NONE": -0.1682723158645361, "mode_PIECEWISE": -0.05341411394958018, "prefill_fraction": -0.12905587442539998, "scheduled_tokens": -0.09951290348812954 }, "valid": false }, "shares": { "attention": 0.3087850643091725, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.005163136163815447, "moe_gemm": 0.5777999387887653, "moe_router": 0.02008575072504131, "norm_elementwise": 0.07341833511421153, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 583.5649999999997, "name": "triton_poi_fused_3" }, { "duration_us": 466.8209999999995, "name": "triton_red_fused_2" }, { "duration_us": 19.617, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.536, "name": "triton_poi_fused_2" }, { "duration_us": 11.231999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 10.049, "name": "triton_red_fused_1" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783849466906401944.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.3033378915990537, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9736215707793747, "mode_shares": { "FULL": { "attention": 0.3033378915990537, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.008423712471036498, "moe_gemm": 0.5030357454817748, "moe_router": 0.03618969859772223, "norm_elementwise": 0.12263452262978754, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.026378429220625322, "representativeness": { "smd": { "decode_batch_size": -0.5055344205281964, "mode_FULL": 0.17677689026422408, "mode_NONE": -0.1682723158645361, "mode_PIECEWISE": -0.05341411394958018, "prefill_fraction": -0.12905587442539998, "scheduled_tokens": -0.10506250419671144 }, "valid": false }, "shares": { "attention": 0.3033378915990537, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.008423712471036498, "moe_gemm": 0.5030357454817748, "moe_router": 0.03618969859772223, "norm_elementwise": 0.12263452262978754, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 590.9459999999992, "name": "triton_poi_fused_3" }, { "duration_us": 467.6929999999989, "name": "triton_red_fused_2" }, { "duration_us": 18.272, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.152, "name": "triton_poi_fused_2" }, { "duration_us": 9.63, "name": "triton_red_fused_1" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783849498465727706.pt.trace.json.gz" } ], "P10-C00-saturation": [ { "attention_subshares": { "attention_decode": 0.7471257503417844, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9942106688319626, "mode_shares": { "FULL": { "attention": 0.7471257503417844, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0013626029325187864, "moe_gemm": 0.21782046124566493, "moe_router": 0.009663599861937516, "norm_elementwise": 0.01823825445005707, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.005789331168037346, "representativeness": { "smd": { "decode_batch_size": 3.613259323224499, "mode_FULL": 0.6120018940246724, "mode_NONE": -0.5981417765928579, "mode_PIECEWISE": -0.10976470169608525, "prefill_fraction": -0.6117521895228502, "scheduled_tokens": -0.5755060211990467 }, "valid": false }, "shares": { "attention": 0.7471257503417844, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0013626029325187864, "moe_gemm": 0.21782046124566493, "moe_router": 0.009663599861937516, "norm_elementwise": 0.01823825445005707, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 637.9129999999991, "name": "triton_poi_fused_3" }, { "duration_us": 513.3399999999995, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 484.63699999999847, "name": "triton_red_fused_2" }, { "duration_us": 19.874, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.408, "name": "triton_poi_fused_2" }, { "duration_us": 10.879999999999999, "name": "triton_red_fused_1" }, { "duration_us": 10.305, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783848740596577354.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.2679713777414123, "attention_mixed": 0.3408621380286316, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9943826035261398, "mode_shares": { "FULL": { "attention": 0.6506807095871076, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001469412163770193, "moe_gemm": 0.3120351814822058, "moe_router": 0.01012812440986268, "norm_elementwise": 0.0195308311121687, "sampler": 0.0 }, "NONE": { "attention": 0.5795322961533458, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.39390960062584945, "moe_router": 0.0023577446138654075, "norm_elementwise": 0.01895990875545615, "sampler": 0.0 } }, "mode_steps": { "FULL": 7, "NONE": 1 }, "other_share": 0.005617396473860218, "representativeness": { "smd": { "decode_batch_size": 28.040640400381754, "mode_FULL": 0.09182576274871186, "mode_NONE": -0.07574082366962798, "mode_PIECEWISE": -0.10976470169608525, "prefill_fraction": -0.09431170009009414, "scheduled_tokens": -0.3287773474224777 }, "valid": false }, "shares": { "attention": 0.6088335157700439, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0006051514916514902, "moe_gemm": 0.36019106467352013, "moe_router": 0.005557838529095687, "norm_elementwise": 0.019195033061828647, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1568.3549999999968, "name": "triton_poi_fused_3" }, { "duration_us": 937.5360000000019, "name": "triton_red_fused_2" }, { "duration_us": 870.9730000000023, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 32.38400000000001, "name": "triton_poi_fused_2" }, { "duration_us": 25.343999999999998, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 21.376, "name": "triton_red_fused_1" }, { "duration_us": 11.167999999999997, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783848774099957127.pt.trace.json.gz" } ], "P10-C01-moderate": [ { "attention_subshares": { "attention_decode": 0.00827308232619546, "attention_mixed": 0.0, "attention_prefill": 0.3878891624260789 }, "classifiable_fraction": 0.9920412642157855, "mode_shares": { "FULL": { "attention": 0.24862667112394968, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.009001841356572508, "moe_gemm": 0.5445479195579913, "moe_router": 0.038657214941041004, "norm_elementwise": 0.1306799512400259, "sampler": 0.0 }, "NONE": { "attention": 0.3919918323373639, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.5695375481303059, "moe_router": 0.004010888023206571, "norm_elementwise": 0.027034253877755012, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.47297055300102214, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001160843915130027, "moe_gemm": 0.49362762525763404, "moe_router": 0.006709457074185478, "norm_elementwise": 0.0196235305449198, "sampler": 0.0 } }, "mode_steps": { "FULL": 4, "NONE": 3, "PIECEWISE": 1 }, "other_share": 0.007958735784214513, "representativeness": { "smd": { "decode_batch_size": -1.315856674395644, "mode_FULL": -1.1873139780953184, "mode_NONE": 0.904151999012294, "mode_PIECEWISE": 0.4906969552687828, "prefill_fraction": 1.2174104966136614, "scheduled_tokens": 1.0338890364922466 }, "valid": false }, "shares": { "attention": 0.39616224475227435, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0004277067707998268, "moe_gemm": 0.5603247586456352, "moe_router": 0.005461699212612277, "norm_elementwise": 0.029664854834463707, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 2284.6260000000075, "name": "triton_poi_fused_3" }, { "duration_us": 1233.3779999999972, "name": "triton_red_fused_2" }, { "duration_us": 986.3160000000001, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 48.257000000000005, "name": "triton_poi_fused_2" }, { "duration_us": 27.777000000000005, "name": "triton_red_fused_1" }, { "duration_us": 23.712000000000003, "name": "_compute_slot_mapping_kernel" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783836534095748867.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.0063747668464849165, "attention_mixed": 0.15479011673996892, "attention_prefill": 0.3931831065712863 }, "classifiable_fraction": 0.9945037369811328, "mode_shares": { "FULL": { "attention": 0.3498249631356147, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.006205452478989364, "moe_gemm": 0.505172700292536, "moe_router": 0.026126956515180367, "norm_elementwise": 0.09328180537085141, "sampler": 0.0 }, "NONE": { "attention": 0.5581441347693616, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.4145765883773621, "moe_router": 0.0028266883400090486, "norm_elementwise": 0.019214171797428074, "sampler": 0.0 } }, "mode_steps": { "FULL": 3, "NONE": 5 }, "other_share": 0.005496263018867143, "representativeness": { "smd": { "decode_batch_size": -0.21484041020694733, "mode_FULL": -1.5472770324498917, "mode_NONE": 1.55520654375562, "mode_PIECEWISE": -0.055941052979459574, "prefill_fraction": 1.5826586640498834, "scheduled_tokens": 1.5981896236261708 }, "valid": false }, "shares": { "attention": 0.5543479901577401, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.00011308030272031699, "moe_gemm": 0.41622749712178303, "moe_router": 0.0032512829022321816, "norm_elementwise": 0.020563886496657274, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 3222.5210000000084, "name": "triton_poi_fused_3" }, { "duration_us": 1708.5829999999992, "name": "triton_red_fused_2" }, { "duration_us": 1400.3889999999992, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 68.76799999999999, "name": "triton_poi_fused_2" }, { "duration_us": 37.952, "name": "triton_red_fused_1" }, { "duration_us": 29.728999999999996, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 10.174999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783836573272002789.pt.trace.json.gz" } ], "P10-C10-moderate": [ { "attention_subshares": { "attention_decode": 0.2843977937526034, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9824438147308845, "mode_shares": { "FULL": { "attention": 0.2843977937526034, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.00405010296319307, "moe_gemm": 0.6130100529210382, "moe_router": 0.027604734811478317, "norm_elementwise": 0.05338113028257156, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.017556185269115537, "representativeness": { "smd": { "decode_batch_size": 5.144106307912562, "mode_FULL": 0.18130730690818112, "mode_NONE": -0.1757536966781094, "mode_PIECEWISE": -0.04385290377913636, "prefill_fraction": -0.14497536337962438, "scheduled_tokens": -0.11030736227232732 }, "valid": false }, "shares": { "attention": 0.2843977937526034, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.00405010296319307, "moe_gemm": 0.6130100529210382, "moe_router": 0.027604734811478317, "norm_elementwise": 0.05338113028257156, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 629.6319999999995, "name": "triton_poi_fused_3" }, { "duration_us": 515.3909999999998, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 499.33799999999894, "name": "triton_red_fused_2" }, { "duration_us": 18.209, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.758, "name": "triton_poi_fused_2" }, { "duration_us": 11.359999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 11.105, "name": "triton_red_fused_1" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783838883199166770.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.3547933594800296, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9860169102260189, "mode_shares": { "FULL": { "attention": 0.3547933594800296, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004769401324813265, "moe_gemm": 0.534184946336729, "moe_router": 0.023130978256460693, "norm_elementwise": 0.06913822482798647, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.013983089773981138, "representativeness": { "smd": { "decode_batch_size": 2.258805078083754, "mode_FULL": 0.18130730690818112, "mode_NONE": -0.1757536966781094, "mode_PIECEWISE": -0.04385290377913636, "prefill_fraction": -0.14497536337962438, "scheduled_tokens": -0.11500242829780874 }, "valid": false }, "shares": { "attention": 0.3547933594800296, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004769401324813265, "moe_gemm": 0.534184946336729, "moe_router": 0.023130978256460693, "norm_elementwise": 0.06913822482798647, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 620.6479999999996, "name": "triton_poi_fused_3" }, { "duration_us": 473.21299999999843, "name": "triton_red_fused_2" }, { "duration_us": 19.232, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.408, "name": "triton_poi_fused_2" }, { "duration_us": 11.551999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 9.921, "name": "triton_red_fused_1" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783838915336860515.pt.trace.json.gz" } ], "P10-C10-saturation": [ { "attention_subshares": { "attention_decode": 0.041504399483772915, "attention_mixed": 0.37939509732011933, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9925214098201124, "mode_shares": { "FULL": { "attention": 0.6458307859040855, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001372377547939455, "moe_gemm": 0.3195152761398567, "moe_router": 0.008996381149482991, "norm_elementwise": 0.01843126133535932, "sampler": 0.0 }, "NONE": { "attention": 0.4054514900827006, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.5564249519780634, "moe_router": 0.0027817925221303996, "norm_elementwise": 0.027751594727275442, "sampler": 0.0 } }, "mode_steps": { "FULL": 4, "NONE": 4 }, "other_share": 0.007478590179887577, "representativeness": { "smd": { "decode_batch_size": 3.1738421486850954, "mode_FULL": -0.7499688060387298, "mode_NONE": 0.7499688060387298, "mode_PIECEWISE": 0.0, "prefill_fraction": 0.7578037492611197, "scheduled_tokens": 0.774707112934012 }, "valid": false }, "shares": { "attention": 0.4208994968038922, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 8.81960216754039e-05, "moe_gemm": 0.5411999208365155, "moe_router": 0.0031811738688339005, "norm_elementwise": 0.027152622289195533, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 9201.402000000015, "name": "triton_poi_fused_3" }, { "duration_us": 4652.703000000019, "name": "triton_red_fused_2" }, { "duration_us": 3948.9770000000117, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 195.13799999999998, "name": "triton_poi_fused_2" }, { "duration_us": 99.81200000000001, "name": "triton_red_fused_1" }, { "duration_us": 50.913000000000004, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 12.383999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783838157121058985.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.6315023261702531, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9935622263304319, "mode_shares": { "FULL": { "attention": 0.6315023261702531, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0015181468521158754, "moe_gemm": 0.33046383055037754, "moe_router": 0.009848784918527526, "norm_elementwise": 0.020229137839157803, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.006437773669568139, "representativeness": { "smd": { "decode_batch_size": 5.3541833543837525, "mode_FULL": 0.6097616511341267, "mode_NONE": -0.6097616511341267, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.6046345482385058, "scheduled_tokens": -0.573070382452099 }, "valid": false }, "shares": { "attention": 0.6315023261702531, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0015181468521158754, "moe_gemm": 0.33046383055037754, "moe_router": 0.009848784918527526, "norm_elementwise": 0.020229137839157803, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 707.0429999999991, "name": "triton_poi_fused_3" }, { "duration_us": 532.921999999999, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 508.57699999999977, "name": "triton_red_fused_2" }, { "duration_us": 19.582, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.630999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 11.838999999999997, "name": "triton_red_fused_1" }, { "duration_us": 10.496, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783838196792063539.pt.trace.json.gz" } ], "P10-C11-moderate": [ { "attention_subshares": { "attention_decode": 0.0073359442575772465, "attention_mixed": 0.3947369166548715, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9927989737523812, "mode_shares": { "FULL": { "attention": 0.5045602577486049, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.002961104894369635, "moe_gemm": 0.4165724542443657, "moe_router": 0.022869450932386057, "norm_elementwise": 0.040255165110812396, "sampler": 0.0 }, "NONE": { "attention": 0.40056078314413623, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.5626074540524005, "moe_router": 0.0039472613290762685, "norm_elementwise": 0.02576580936708546, "sampler": 0.0 } }, "mode_steps": { "FULL": 1, "NONE": 7 }, "other_share": 0.0072010262476187884, "representativeness": { "smd": { "decode_batch_size": 6.315536403064479, "mode_FULL": -3.018625091009808, "mode_NONE": 3.026618811087864, "mode_PIECEWISE": -0.035519441883670656, "prefill_fraction": 3.0955670336388525, "scheduled_tokens": 2.775871694111727 }, "valid": false }, "shares": { "attention": 0.40207286091244876, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 4.305234134543738e-05, "moe_gemm": 0.560484209897129, "moe_router": 0.004222376394183816, "norm_elementwise": 0.025976474207274176, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 4037.0970000000043, "name": "triton_poi_fused_3" }, { "duration_us": 2121.486000000002, "name": "triton_red_fused_2" }, { "duration_us": 1910.3059999999973, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 85.40900000000002, "name": "triton_poi_fused_2" }, { "duration_us": 45.473000000000006, "name": "triton_red_fused_1" }, { "duration_us": 32.478, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 11.264999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783848267170744798.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.2585417693591813, "attention_mixed": 0.16843822503094136, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9906404216693048, "mode_shares": { "FULL": { "attention": 0.539559922335815, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0024951724086338385, "moe_gemm": 0.3941567666483815, "moe_router": 0.019165126164455013, "norm_elementwise": 0.03398857365164246, "sampler": 0.0 }, "NONE": { "attention": 0.3234044301174878, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6347896864036598, "moe_router": 0.004354761640020028, "norm_elementwise": 0.02926443812587131, "sampler": 0.0 } }, "mode_steps": { "FULL": 7, "NONE": 1 }, "other_share": 0.009359578330695272, "representativeness": { "smd": { "decode_batch_size": 9.434244196050145, "mode_FULL": -0.33301959680175525, "mode_NONE": 0.33591397118576066, "mode_PIECEWISE": -0.035519441883670656, "prefill_fraction": 0.3608423156901009, "scheduled_tokens": 0.38343744134224045 }, "valid": false }, "shares": { "attention": 0.42697999439012263, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001195615653941949, "moe_gemm": 0.5194852350087792, "moe_router": 0.01145146710403092, "norm_elementwise": 0.03152810951243005, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1147.1800000000003, "name": "triton_poi_fused_3" }, { "duration_us": 753.7689999999993, "name": "triton_red_fused_2" }, { "duration_us": 745.4559999999998, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 24.256, "name": "triton_poi_fused_2" }, { "duration_us": 21.409000000000002, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 16.959, "name": "triton_red_fused_1" }, { "duration_us": 11.647999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783848309990988798.pt.trace.json.gz" } ], "P10-C11-saturation": [ { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.6985892713346192, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9963781377235988, "mode_shares": { "NONE": { "attention": 0.6985892713346192, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.28271066266772416, "moe_router": 0.0019371533585066747, "norm_elementwise": 0.013141050362748694, "sampler": 0.0 } }, "mode_steps": { "NONE": 8 }, "other_share": 0.0036218622764011715, "representativeness": { "smd": { "decode_batch_size": -1.3424985614091869, "mode_FULL": -1.2678999201712284, "mode_NONE": 1.2792167933527154, "mode_PIECEWISE": -0.09386487859221887, "prefill_fraction": 1.2748539687576104, "scheduled_tokens": 1.3073041498709979 }, "valid": false }, "shares": { "attention": 0.6985892713346192, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.28271066266772416, "moe_router": 0.0019371533585066747, "norm_elementwise": 0.013141050362748694, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 4839.693000000004, "name": "triton_poi_fused_3" }, { "duration_us": 2523.400000000001, "name": "triton_red_fused_2" }, { "duration_us": 2258.809, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 102.399, "name": "triton_poi_fused_2" }, { "duration_us": 53.057, "name": "triton_red_fused_1" }, { "duration_us": 34.175000000000004, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 10.751999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783847496152835877.pt.trace.json.gz" }, { "attention_subshares": { "attention_decode": 0.623103669396033, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9937738750743762, "mode_shares": { "FULL": { "attention": 0.623103669396033, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0014430357241519828, "moe_gemm": 0.3399197180195412, "moe_router": 0.009702122794559957, "norm_elementwise": 0.019605329140090146, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "other_share": 0.006226124925623746, "representativeness": { "smd": { "decode_batch_size": 15.677343907178292, "mode_FULL": 1.5739447284884216, "mode_NONE": -1.5600204796984336, "mode_PIECEWISE": -0.09386487859221887, "prefill_fraction": -1.5730835237401557, "scheduled_tokens": -1.5227269874253568 }, "valid": false }, "shares": { "attention": 0.623103669396033, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0014430357241519828, "moe_gemm": 0.3399197180195412, "moe_router": 0.009702122794559957, "norm_elementwise": 0.019605329140090146, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 701.6779999999983, "name": "triton_poi_fused_3" }, { "duration_us": 536.7749999999995, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 511.6289999999995, "name": "triton_red_fused_2" }, { "duration_us": 20.16, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.888, "name": "triton_poi_fused_2" }, { "duration_us": 11.646999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 10.720999999999998, "name": "triton_red_fused_1" } ], "trace": "dp0_pp0_tp0_dcp0_ep0_rank0.1783847541459857339.pt.trace.json.gz" } ] }, "analysis_seed": 20260714, "bootstrap_resamples": 100000, "hypothesis": { "H1a": "INCONCLUSIVE", "H1b": "PASS", "compound": "PARTIAL", "h1b_hits": [ { "available": true, "ci95_high": 0.23494534783397408, "ci95_low": 0.2253590527218157, "coincident_efficiency_or_residual": true, "control": "P02", "efficiency_loss": 0.11608997226921058, "evaluable": true, "irregular": "P06", "material": true, "metric": "R64", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.2301483528866904, "simultaneous_high": 0.23683442206671917, "simultaneous_low": 0.22345003461028415 }, { "available": true, "ci95_high": 0.3588237662068493, "ci95_low": 0.34996301147907066, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.2284629366493368, "evaluable": true, "irregular": "P06", "material": true, "metric": "R64", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.3543970834375052, "simultaneous_high": 0.3605880124391376, "simultaneous_low": 0.34826154238421436 }, { "available": true, "ci95_high": 0.07258101928545771, "ci95_low": 0.06107199918894719, "coincident_efficiency_or_residual": true, "control": "P01", "efficiency_loss": 0.08324816211784114, "evaluable": true, "irregular": "P09", "material": true, "metric": "padding_fraction", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.0667290414201105, "simultaneous_high": 0.07492451384312424, "simultaneous_low": 0.058870086990988876 }, { "available": true, "ci95_high": 0.4001054362524198, "ci95_low": 0.3922157126916775, "coincident_efficiency_or_residual": true, "control": "P01", "efficiency_loss": 0.08324816211784114, "evaluable": true, "irregular": "P09", "material": true, "metric": "R64", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.39616418510901036, "simultaneous_high": 0.4016625621683738, "simultaneous_low": 0.3906536566040832 }, { "available": true, "ci95_high": 0.08855777444708128, "ci95_low": 0.027415277773332525, "coincident_efficiency_or_residual": true, "control": "P03", "efficiency_loss": 0.4469310402722787, "evaluable": true, "irregular": "P10", "material": true, "metric": "padding_fraction", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.05565211993295673, "simultaneous_high": 0.10341073102256013, "simultaneous_low": 0.020097017796153225 }, { "available": true, "ci95_high": 0.4561736305824604, "ci95_low": 0.43955479496868705, "coincident_efficiency_or_residual": true, "control": "P03", "efficiency_loss": 0.4469310402722787, "evaluable": true, "irregular": "P10", "material": true, "metric": "R64", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.4478716685574937, "simultaneous_high": 0.459713780733712, "simultaneous_low": 0.43635435003093426 }, { "available": true, "ci95_high": 0.08668052314167546, "ci95_low": 0.025823274229141942, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.1425966128421564, "evaluable": true, "irregular": "P10", "material": true, "metric": "padding_fraction", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.05398526806052646, "simultaneous_high": 0.10213016668480329, "simultaneous_low": 0.018683381445978635 }, { "available": true, "ci95_high": 0.45618061702156487, "ci95_low": 0.4395710696329076, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.1425966128421564, "evaluable": true, "irregular": "P10", "material": true, "metric": "R64", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.4478716685574937, "simultaneous_high": 0.4594884290583298, "simultaneous_low": 0.4363807227134572 } ], "logical_asymmetry": "A-P3-7 permits existential confirmation but incomplete coverage forbids refutation", "refutation_allowed": false }, "matrix": { "clean_window_failures": 0, "complete_cells": [ "P01/C00", "P01/C01", "P01/C10", "P01/C11", "P02/C00", "P03/C00", "P03/C01", "P03/C10", "P04/C00", "P06/C00", "P06/C01", "P06/C10", "P06/C11", "P07/C00", "P08/C00", "P09/C00", "P10/C00", "P10/C01", "P10/C10", "P10/C11" ], "completed_c00_patterns": [ "P01", "P02", "P03", "P04", "P06", "P07", "P08", "P09", "P10" ], "confirmation_runs": 0, "drain_quarantined_runs": 0, "gpu_hours_total": 14.025875418755744, "missing_cells": [ "P03/C11", "P05/C00", "P10/C00-TP2", "P11/C00" ], "primary_runs": 40, "trace_files": 72 }, "operational_findings": { "failure_boundary": { "clean_failures": 0, "excluded_failure_kinds": { "ServerDisconnectedError": 2 }, "excluded_window_failures": 2, "run_id": "P01-C01-moderate" }, "layer2_sampling": { "classifiable_fraction_min": 0.9704584620048622, "completed_c00_moderate_patterns": 9, "evaluable_c00_moderate_patterns": 1, "invalid_windows": 16 }, "long_context_drain": { "amended_budget_seconds": 600, "drain_seconds": 288.6191079240234, "quarantined": false, "run_id": "P10-C01-saturation" }, "p10_tp2_non_stabilization": { "accepted_measurement": false, "comparison": "all synthetic pattern runs passed their applicable registered warm-up gates; orchestrator adjudication", "mean_scheduled_token_throughput": 16156.333333333334, "normalized_drift": 0.367639109533929, "normalized_drift_limit": 0.1, "passes": false, "same_wave_synthetic_warmup_completions": { "P03-C11": 102, "P11-C00": 512 }, "scheduled_token_throughput": [ 18022.4, 16384.0, 14062.6 ], "scheduled_tokens": [ 90112, 81920, 70313 ], "slope_tokens_per_second_squared": -395.98000000000013, "status": "PATTERN_CONDITIONED_OPERATIONAL_FINDING", "step_counts": [ 11, 10, 16 ], "warmup_completions": 17 } }, "operator_mode_segments": { "P01-C00-moderate": { "PIECEWISE": { "other_share": 0.009442586767856639, "shares": { "attention": 0.14059860036997104, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.002034731217402245, "moe_gemm": 0.8039268095204102, "moe_router": 0.011615692688783654, "norm_elementwise": 0.03238157943557617, "sampler": 0.0 }, "steps": 9 } }, "P01-C00-saturation": { "FULL": { "other_share": 0.008640959425607062, "shares": { "attention": 0.24548760946422593, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0018953885436714586, "moe_gemm": 0.6964242752814832, "moe_router": 0.01232208790526271, "norm_elementwise": 0.035229679379749704, "sampler": 0.0 }, "steps": 9 } }, "P02-C00-moderate": { "FULL": { "other_share": 0.010310329169884497, "shares": { "attention": 0.2078704033504826, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0025993696985651725, "moe_gemm": 0.7238420167249907, "moe_router": 0.01747338449479615, "norm_elementwise": 0.03790449656128083, "sampler": 0.0 }, "steps": 14 } }, "P02-C00-saturation": { "FULL": { "other_share": 0.007432424187256434, "shares": { "attention": 0.3275775913752123, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0016046133640397883, "moe_gemm": 0.6231403899130352, "moe_router": 0.010494318932798818, "norm_elementwise": 0.029750662227657432, "sampler": 0.0 }, "steps": 16 } }, "P03-C00-moderate": { "FULL": { "other_share": 0.02536523149315264, "shares": { "attention": 0.23362801063108302, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.00817304104316153, "moe_gemm": 0.5766381826618499, "moe_router": 0.03482203360681858, "norm_elementwise": 0.12137350056393428, "sampler": 0.0 }, "steps": 16 } }, "P03-C00-saturation": { "NONE": { "other_share": 0.008588238863572845, "shares": { "attention": 0.3425157512172391, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6147796482452442, "moe_router": 0.0032160079024607783, "norm_elementwise": 0.03090035377148312, "sampler": 0.0 }, "steps": 9 } }, "P04-C00-moderate": { "FULL": { "other_share": 0.018960704531611056, "shares": { "attention": 0.4787340825464985, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004481448763560187, "moe_gemm": 0.40647901207594744, "moe_router": 0.03279818524077843, "norm_elementwise": 0.058546566841604454, "sampler": 0.0 }, "steps": 16 } }, "P04-C00-saturation": { "FULL": { "other_share": 0.007202580412325669, "shares": { "attention": 0.6587156975804976, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0017451569361964714, "moe_gemm": 0.2978006885644627, "moe_router": 0.0115658672042958, "norm_elementwise": 0.022970009302221747, "sampler": 0.0 }, "steps": 16 } }, "P06-C00-moderate": { "FULL": { "other_share": 0.017142137497054708, "shares": { "attention": 0.33107685878416826, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004081391199666314, "moe_gemm": 0.5650713814732576, "moe_router": 0.028378480372589072, "norm_elementwise": 0.05424975067326402, "sampler": 0.0 }, "steps": 16 } }, "P06-C00-saturation": { "FULL": { "other_share": 0.006199138768841979, "shares": { "attention": 0.5659533573255217, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0015410952588019783, "moe_gemm": 0.3933982154583866, "moe_router": 0.010416018392470881, "norm_elementwise": 0.022492174795976858, "sampler": 0.0 }, "steps": 16 } }, "P07-C00-moderate": { "FULL": { "other_share": 0.014869887132538163, "shares": { "attention": 0.2852930717632125, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003706604156207189, "moe_gemm": 0.623593410175782, "moe_router": 0.0240999362809864, "norm_elementwise": 0.0484370904912738, "sampler": 0.0 }, "steps": 16 } }, "P08-C00-moderate": { "FULL": { "other_share": 0.013318198191355927, "shares": { "attention": 0.3439533361307738, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003386612631774027, "moe_gemm": 0.5732681692206052, "moe_router": 0.021994246442847046, "norm_elementwise": 0.0440794373826441, "sampler": 0.0 }, "steps": 16 } }, "P09-C00-moderate": { "FULL": { "other_share": 0.018491839460411715, "shares": { "attention": 0.21168617810937532, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.005229294671508251, "moe_gemm": 0.675665021622912, "moe_router": 0.030111781499347623, "norm_elementwise": 0.05881588463644517, "sampler": 0.0 }, "steps": 12 } }, "P09-C00-saturation": { "NONE": { "other_share": 0.0095175085506292, "shares": { "attention": 0.26265552511434637, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6899598757335755, "moe_router": 0.003553959807497156, "norm_elementwise": 0.03431313079395171, "sampler": 0.0 }, "steps": 16 } }, "P10-C00-moderate": { "FULL": { "other_share": 0.01890606961699496, "shares": { "attention": 0.30683754279558073, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.006328886332379883, "moe_gemm": 0.5510695811040863, "moe_router": 0.025843377039614774, "norm_elementwise": 0.09101454311134333, "sampler": 0.0 }, "steps": 16 } }, "P10-C00-saturation": { "FULL": { "other_share": 0.005959860267121688, "shares": { "attention": 0.7022397416038559, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001412312487823314, "moe_gemm": 0.2616684675577343, "moe_router": 0.009879791931057879, "norm_elementwise": 0.01883982615240685, "sampler": 0.0 }, "steps": 15 } } }, "operator_share_table": { "P01": { "moderate": { "mean_ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.8242859924840175 }, { "family": "attention", "rank": 2, "share": 0.12088271131609091 }, { "family": "norm_elementwise", "rank": 3, "share": 0.033822363286085066 }, { "family": "moe_router", "rank": 4, "share": 0.010309373428617204 }, { "family": "kv_memory", "rank": 4, "share": 0.0010574407739066686 }, { "family": "collective", "rank": 6, "share": 0.0 }, { "family": "sampler", "rank": 6, "share": 0.0 }, { "family": "dense_gemm", "rank": 6, "share": 0.0 } ], "mean_shares": { "attention": 0.12088271131609091, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0010574407739066686, "moe_gemm": 0.8242859924840175, "moe_router": 0.010309373428617204, "norm_elementwise": 0.033822363286085066, "sampler": 0.0 }, "reason": "classifiability, representativeness, or recovery gate failed", "run_id": "P01-C00-moderate", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 2, "windows": [ { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.11987238161795156, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9905881019946707, "mode_shares": { "NONE": { "attention": 0.1007462687465188, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8471040152242396, "moe_router": 0.008477215998495907, "norm_elementwise": 0.034119643236757626, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.13605518456441312, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0019444790834074754, "moe_gemm": 0.8102627123318585, "moe_router": 0.01080794700368473, "norm_elementwise": 0.03163704570787867, "sampler": 0.0 } }, "mode_steps": { "NONE": 3, "PIECEWISE": 5 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.8271478398184453 }, { "family": "attention", "rank": 2, "share": 0.11987238161795156 }, { "family": "norm_elementwise", "rank": 3, "share": 0.032774871259148075 }, { "family": "moe_router", "rank": 4, "share": 0.009739725006365179 }, { "family": "kv_memory", "rank": 4, "share": 0.0010532842927605177 }, { "family": "collective", "rank": 4, "share": 0.0 }, { "family": "sampler", "rank": 4, "share": 0.0 }, { "family": "dense_gemm", "rank": 4, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 2.4721524781047854, "mode_FULL": -0.2325584995849942, "mode_NONE": 0.3041456447839143, "mode_PIECEWISE": -0.24468169875030038, "prefill_fraction": 0.18099057277285577, "scheduled_tokens": 0.4474608400278538 }, "valid": false }, "shares": { "attention": 0.11987238161795156, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0010532842927605177, "moe_gemm": 0.8271478398184453, "moe_router": 0.009739725006365179, "norm_elementwise": 0.032774871259148075, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1567.9510000000005, "name": "triton_poi_fused_3" }, { "duration_us": 933.1070000000002, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 827.689, "name": "triton_red_fused_2" }, { "duration_us": 33.057, "name": "triton_poi_fused_2" }, { "duration_us": 22.368999999999996, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 17.247, "name": "triton_red_fused_1" }, { "duration_us": 11.647999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.008867955248024707, "attention_mixed": 0.11302508576620553, "attention_prefill": 0.0 }, "classifiable_fraction": 0.990127660582764, "mode_shares": { "FULL": { "attention": 0.16315875281832684, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0031741793017298413, "moe_gemm": 0.7536332801624461, "moe_router": 0.02179864485086512, "norm_elementwise": 0.045434533244984684, "sampler": 0.0 }, "NONE": { "attention": 0.09828250109360281, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8488043657595763, "moe_router": 0.008302816259724543, "norm_elementwise": 0.0348733229605455, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.1472178594517614, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.002166218689199354, "moe_gemm": 0.7946960932441856, "moe_router": 0.012792489660640699, "norm_elementwise": 0.033466283510587794, "sampler": 0.0 } }, "mode_steps": { "FULL": 1, "NONE": 3, "PIECEWISE": 4 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.8214241451495896 }, { "family": "attention", "rank": 2, "share": 0.12189304101423025 }, { "family": "norm_elementwise", "rank": 3, "share": 0.034869855313022065 }, { "family": "moe_router", "rank": 4, "share": 0.010879021850869232 }, { "family": "kv_memory", "rank": 4, "share": 0.0010615972550528194 }, { "family": "collective", "rank": 6, "share": 0.0 }, { "family": "sampler", "rank": 6, "share": 0.0 }, { "family": "dense_gemm", "rank": 6, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 1.4422983740600546, "mode_FULL": 0.3594518697735859, "mode_NONE": 0.3041456447839143, "mode_PIECEWISE": -0.49598146699059914, "prefill_fraction": -0.3699982864929203, "scheduled_tokens": 0.1504241077629697 }, "valid": false }, "shares": { "attention": 0.12189304101423025, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0010615972550528194, "moe_gemm": 0.8214241451495896, "moe_router": 0.010879021850869232, "norm_elementwise": 0.034869855313022065, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1449.5139999999994, "name": "triton_poi_fused_3" }, { "duration_us": 884.6050000000004, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 826.8859999999994, "name": "triton_red_fused_2" }, { "duration_us": 30.943000000000005, "name": "triton_poi_fused_2" }, { "duration_us": 22.431999999999995, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 17.441, "name": "triton_red_fused_1" }, { "duration_us": 11.328999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 2 } ] }, "saturation": { "mean_ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.778146620509425 }, { "family": "attention", "rank": 2, "share": 0.16322081274999037 }, { "family": "norm_elementwise", "rank": 3, "share": 0.03900169950588005 }, { "family": "moe_router", "rank": 4, "share": 0.008475029742520849 }, { "family": "kv_memory", "rank": 4, "share": 0.0009569388167916614 }, { "family": "collective", "rank": 4, "share": 0.0 }, { "family": "sampler", "rank": 4, "share": 0.0 }, { "family": "dense_gemm", "rank": 4, "share": 0.0 } ], "mean_shares": { "attention": 0.16322081274999037, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0009569388167916614, "moe_gemm": 0.778146620509425, "moe_router": 0.008475029742520849, "norm_elementwise": 0.03900169950588005, "sampler": 0.0 }, "reason": "classifiability, representativeness, or recovery gate failed", "run_id": "P01-C00-saturation", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 2, "windows": [ { "attention_subshares": { "attention_decode": 0.24646421810404764, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9913999320344749, "mode_shares": { "FULL": { "attention": 0.24646421810404764, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0018861985126382374, "moe_gemm": 0.6957077658710443, "moe_router": 0.012274637353427154, "norm_elementwise": 0.03506711219331752, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.6957077658710443 }, { "family": "attention", "rank": 2, "share": 0.24646421810404764 }, { "family": "norm_elementwise", "rank": 3, "share": 0.03506711219331752 }, { "family": "moe_router", "rank": 4, "share": 0.012274637353427154 }, { "family": "kv_memory", "rank": 5, "share": 0.0018861985126382374 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 0.658013698411068, "mode_FULL": 0.6877531107808548, "mode_NONE": -0.6802380609168648, "mode_PIECEWISE": -0.08229232202065807, "prefill_fraction": -0.6816133519618747, "scheduled_tokens": -0.6333120429828512 }, "valid": false }, "shares": { "attention": 0.24646421810404764, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0018861985126382374, "moe_gemm": 0.6957077658710443, "moe_router": 0.012274637353427154, "norm_elementwise": 0.03506711219331752, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1013.7599999999983, "name": "triton_poi_fused_3" }, { "duration_us": 701.0369999999989, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 598.1809999999995, "name": "triton_red_fused_2" }, { "duration_us": 25.409, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 22.721999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 13.697, "name": "triton_red_fused_1" }, { "duration_us": 13.632, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.0033278995815980927, "attention_mixed": 0.07664950781433502, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9882022706147409, "mode_shares": { "FULL": { "attention": 0.2372289894559244, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001973103373413011, "moe_gemm": 0.7024833850537113, "moe_router": 0.0127233500493961, "norm_elementwise": 0.03660441698068597, "sampler": 0.0 }, "NONE": { "attention": 0.07774006222398774, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8628349211839768, "moe_router": 0.004560917765838791, "norm_elementwise": 0.04302637544092451, "sampler": 0.0 } }, "mode_steps": { "FULL": 1, "NONE": 7 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.8605854751478055 }, { "family": "attention", "rank": 2, "share": 0.0799774073959331 }, { "family": "norm_elementwise", "rank": 3, "share": 0.04293628681844257 }, { "family": "moe_router", "rank": 4, "share": 0.0046754221316145424 }, { "family": "kv_memory", "rank": 4, "share": 2.7679120945085497e-05 }, { "family": "collective", "rank": 4, "share": 0.0 }, { "family": "sampler", "rank": 4, "share": 0.0 }, { "family": "dense_gemm", "rank": 4, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -1.184350878588216, "mode_FULL": -1.8269976055369814, "mode_NONE": 1.8429476277592753, "mode_PIECEWISE": -0.08229232202065807, "prefill_fraction": 1.7302789555698612, "scheduled_tokens": 1.471377771158277 }, "valid": false }, "shares": { "attention": 0.0799774073959331, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 2.7679120945085497e-05, "moe_gemm": 0.8605854751478055, "moe_router": 0.0046754221316145424, "norm_elementwise": 0.04293628681844257, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 13829.692000000014, "name": "triton_poi_fused_3" }, { "duration_us": 6941.902000000004, "name": "triton_red_fused_2" }, { "duration_us": 6363.376999999999, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 297.34499999999997, "name": "triton_poi_fused_2" }, { "duration_us": 147.58499999999998, "name": "triton_red_fused_1" }, { "duration_us": 24.673, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 15.264999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 2 } ] } }, "P02": { "moderate": { "mean_ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.7252956001376867 }, { "family": "attention", "rank": 2, "share": 0.2090637894197081 }, { "family": "norm_elementwise", "rank": 3, "share": 0.03675377585093785 }, { "family": "moe_router", "rank": 4, "share": 0.016380325462376815 }, { "family": "kv_memory", "rank": 5, "share": 0.0025049516005055767 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "mean_shares": { "attention": 0.2090637894197081, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0025049516005055767, "moe_gemm": 0.7252956001376867, "moe_router": 0.016380325462376815, "norm_elementwise": 0.03675377585093785, "sampler": 0.0 }, "reason": "classifiability, representativeness, or recovery gate failed", "run_id": "P02-C00-moderate", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 2, "windows": [ { "attention_subshares": { "attention_decode": 0.16431648329180198, "attention_mixed": 0.040375747240313245, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9899496306808163, "mode_shares": { "FULL": { "attention": 0.2070416346282377, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.002614300625672357, "moe_gemm": 0.72402183586612, "moe_router": 0.017564069072735583, "norm_elementwise": 0.03839442593161487, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.19565666700967585, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0017527292718792177, "moe_gemm": 0.7535224022949394, "moe_router": 0.011441473126433909, "norm_elementwise": 0.02878152643291581, "sampler": 0.0 } }, "mode_steps": { "FULL": 7, "PIECEWISE": 1 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.7301095783988965 }, { "family": "attention", "rank": 2, "share": 0.20469223053211524 }, { "family": "norm_elementwise", "rank": 3, "share": 0.036410706151768 }, { "family": "moe_router", "rank": 4, "share": 0.016300609001782734 }, { "family": "kv_memory", "rank": 5, "share": 0.0024365065962538455 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -0.673985188837054, "mode_FULL": 0.11926397031787984, "mode_NONE": -0.2790993472934029, "mode_PIECEWISE": -0.0171348471830914, "prefill_fraction": -0.13753859346790945, "scheduled_tokens": -0.22985353117145157 }, "valid": false }, "shares": { "attention": 0.20469223053211524, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0024365065962538455, "moe_gemm": 0.7301095783988965, "moe_router": 0.016300609001782734, "norm_elementwise": 0.036410706151768, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 775.5859999999996, "name": "triton_poi_fused_3" }, { "duration_us": 562.3350000000004, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 541.5999999999998, "name": "triton_red_fused_2" }, { "duration_us": 22.592, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 16.384, "name": "triton_poi_fused_2" }, { "duration_us": 12.864999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 12.447999999999999, "name": "triton_red_fused_1" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.17098573558976576, "attention_mixed": 0.04244961271753521, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9900472542616138, "mode_shares": { "FULL": { "attention": 0.20867035579310442, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0025849579196340765, "moe_gemm": 0.7236684498934784, "moe_router": 0.017385853018663355, "norm_elementwise": 0.03743160202992195, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.23505546138588368, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0025209396629618792, "moe_gemm": 0.7060220856055816, "moe_router": 0.012259376230707445, "norm_elementwise": 0.035577961118325376, "sampler": 0.0 } }, "mode_steps": { "FULL": 7, "PIECEWISE": 1 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.7204816218764769 }, { "family": "attention", "rank": 2, "share": 0.21343534830730096 }, { "family": "norm_elementwise", "rank": 3, "share": 0.03709684555010769 }, { "family": "moe_router", "rank": 4, "share": 0.016460041922970896 }, { "family": "kv_memory", "rank": 5, "share": 0.0025733966047573075 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 14.182091081480554, "mode_FULL": 0.11926397031787984, "mode_NONE": -0.2790993472934029, "mode_PIECEWISE": -0.0171348471830914, "prefill_fraction": -0.20596870108215656, "scheduled_tokens": -0.2935716394203467 }, "valid": false }, "shares": { "attention": 0.21343534830730096, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0025733966047573075, "moe_gemm": 0.7204816218764769, "moe_router": 0.016460041922970896, "norm_elementwise": 0.03709684555010769, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 767.5569999999994, "name": "triton_poi_fused_3" }, { "duration_us": 572.6729999999994, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 527.8730000000002, "name": "triton_red_fused_2" }, { "duration_us": 22.624999999999996, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 16.192999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 12.735999999999999, "name": "triton_red_fused_1" }, { "duration_us": 11.902999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 2 } ] }, "saturation": { "mean_ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.6239343487636664 }, { "family": "attention", "rank": 2, "share": 0.3267032207444448 }, { "family": "norm_elementwise", "rank": 3, "share": 0.0298005081329104 }, { "family": "moe_router", "rank": 4, "share": 0.010510163136034627 }, { "family": "kv_memory", "rank": 4, "share": 0.0016074078701660255 }, { "family": "collective", "rank": 6, "share": 0.0 }, { "family": "sampler", "rank": 6, "share": 0.0 }, { "family": "dense_gemm", "rank": 6, "share": 0.0 } ], "mean_shares": { "attention": 0.3267032207444448, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0016074078701660255, "moe_gemm": 0.6239343487636664, "moe_router": 0.010510163136034627, "norm_elementwise": 0.0298005081329104, "sampler": 0.0 }, "reason": "classifiability, representativeness, or recovery gate failed", "run_id": "P02-C00-saturation", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 2, "windows": [ { "attention_subshares": { "attention_decode": 0.3066236078963298, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9922817455017883, "mode_shares": { "FULL": { "attention": 0.3066236078963298, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0016715827167837374, "moe_gemm": 0.6421673334694945, "moe_router": 0.010874019669713833, "norm_elementwise": 0.030945201749466352, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.6421673334694945 }, { "family": "attention", "rank": 2, "share": 0.3066236078963298 }, { "family": "norm_elementwise", "rank": 3, "share": 0.030945201749466352 }, { "family": "moe_router", "rank": 4, "share": 0.010874019669713833 }, { "family": "kv_memory", "rank": 4, "share": 0.0016715827167837374 }, { "family": "collective", "rank": 6, "share": 0.0 }, { "family": "sampler", "rank": 6, "share": 0.0 }, { "family": "dense_gemm", "rank": 6, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 0.20138501290112165, "mode_FULL": 0.20658265838024312, "mode_NONE": -0.20080594382714848, "mode_PIECEWISE": -0.04755171103421909, "prefill_fraction": -0.2043665285851284, "scheduled_tokens": -0.19254510985844397 }, "valid": true }, "shares": { "attention": 0.3066236078963298, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0016715827167837374, "moe_gemm": 0.6421673334694945, "moe_router": 0.010874019669713833, "norm_elementwise": 0.030945201749466352, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 996.7139999999991, "name": "triton_poi_fused_3" }, { "duration_us": 703.9869999999992, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 606.911, "name": "triton_red_fused_2" }, { "duration_us": 24.991999999999997, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 21.758999999999997, "name": "triton_poi_fused_2" }, { "duration_us": 13.247, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 13.184, "name": "triton_red_fused_1" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.34678283359255974, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9928295517926563, "mode_shares": { "FULL": { "attention": 0.34678283359255974, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0015432330235483139, "moe_gemm": 0.6057013640578384, "moe_router": 0.010146306602355423, "norm_elementwise": 0.028655814516354454, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.6057013640578384 }, { "family": "attention", "rank": 2, "share": 0.34678283359255974 }, { "family": "norm_elementwise", "rank": 3, "share": 0.028655814516354454 }, { "family": "moe_router", "rank": 4, "share": 0.010146306602355423 }, { "family": "kv_memory", "rank": 4, "share": 0.0015432330235483139 }, { "family": "collective", "rank": 6, "share": 0.0 }, { "family": "sampler", "rank": 6, "share": 0.0 }, { "family": "dense_gemm", "rank": 6, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 0.20138501290112165, "mode_FULL": 0.20658265838024312, "mode_NONE": -0.20080594382714848, "mode_PIECEWISE": -0.04755171103421909, "prefill_fraction": -0.2043665285851284, "scheduled_tokens": -0.19254510985844397 }, "valid": true }, "shares": { "attention": 0.34678283359255974, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0015432330235483139, "moe_gemm": 0.6057013640578384, "moe_router": 0.010146306602355423, "norm_elementwise": 0.028655814516354454, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1013.8929999999987, "name": "triton_poi_fused_3" }, { "duration_us": 711.0099999999981, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 613.2400000000005, "name": "triton_red_fused_2" }, { "duration_us": 25.055, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 22.112, "name": "triton_poi_fused_2" }, { "duration_us": 14.049, "name": "triton_red_fused_1" }, { "duration_us": 13.855, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 2 } ] } }, "P03": { "moderate": { "mean_ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5745120568231603 }, { "family": "attention", "rank": 2, "share": 0.23318306938126201 }, { "family": "norm_elementwise", "rank": 3, "share": 0.12285482042003387 }, { "family": "moe_router", "rank": 4, "share": 0.035409526402454435 }, { "family": "kv_memory", "rank": 5, "share": 0.008296375954773179 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "mean_shares": { "attention": 0.23318306938126201, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.008296375954773179, "moe_gemm": 0.5745120568231603, "moe_router": 0.035409526402454435, "norm_elementwise": 0.12285482042003387, "sampler": 0.0 }, "reason": "classifiability, representativeness, or recovery gate failed", "run_id": "P03-C00-moderate", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 2, "windows": [ { "attention_subshares": { "attention_decode": 0.23677440452100923, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9773142909813943, "mode_shares": { "FULL": { "attention": 0.23677440452100923, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.007300880477096696, "moe_gemm": 0.5916730425467414, "moe_router": 0.030667589074404745, "norm_elementwise": 0.11089837436214241, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5916730425467414 }, { "family": "attention", "rank": 2, "share": 0.23677440452100923 }, { "family": "norm_elementwise", "rank": 3, "share": 0.11089837436214241 }, { "family": "moe_router", "rank": 4, "share": 0.030667589074404745 }, { "family": "kv_memory", "rank": 5, "share": 0.007300880477096696 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 3.72009366381467, "mode_FULL": 0.27793577928319474, "mode_NONE": -0.27793577928319446, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.1868864933066391, "scheduled_tokens": -0.182101722961305 }, "valid": false }, "shares": { "attention": 0.23677440452100923, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.007300880477096696, "moe_gemm": 0.5916730425467414, "moe_router": 0.030667589074404745, "norm_elementwise": 0.11089837436214241, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 576.23, "name": "triton_poi_fused_3" }, { "duration_us": 464.7449999999998, "name": "triton_red_fused_2" }, { "duration_us": 19.744, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 12.575, "name": "triton_poi_fused_2" }, { "duration_us": 11.040999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 9.41, "name": "triton_red_fused_1" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.2295917342415148, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9711974069819732, "mode_shares": { "FULL": { "attention": 0.2295917342415148, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.009291871432449663, "moe_gemm": 0.5573510710995793, "moe_router": 0.04015146373050413, "norm_elementwise": 0.13481126647792535, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5573510710995793 }, { "family": "attention", "rank": 2, "share": 0.2295917342415148 }, { "family": "norm_elementwise", "rank": 3, "share": 0.13481126647792535 }, { "family": "moe_router", "rank": 4, "share": 0.04015146373050413 }, { "family": "kv_memory", "rank": 5, "share": 0.009291871432449663 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -0.27750213252727524, "mode_FULL": 0.27793577928319474, "mode_NONE": -0.27793577928319446, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.1868864933066391, "scheduled_tokens": -0.1838557206293655 }, "valid": false }, "shares": { "attention": 0.2295917342415148, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.009291871432449663, "moe_gemm": 0.5573510710995793, "moe_router": 0.04015146373050413, "norm_elementwise": 0.13481126647792535, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 571.9689999999993, "name": "triton_poi_fused_3" }, { "duration_us": 469.85699999999855, "name": "triton_red_fused_2" }, { "duration_us": 18.529, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 12.383, "name": "triton_poi_fused_2" }, { "duration_us": 9.761000000000001, "name": "triton_red_fused_1" } ], "valid": false, "window": 2 } ] }, "saturation": { "mean_ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5660210180238645 }, { "family": "attention", "rank": 2, "share": 0.3911264870692061 }, { "family": "norm_elementwise", "rank": 3, "share": 0.02983320960479998 }, { "family": "moe_router", "rank": 4, "share": 0.004378996059032046 }, { "family": "kv_memory", "rank": 4, "share": 0.000268750902798599 }, { "family": "collective", "rank": 4, "share": 0.0 }, { "family": "sampler", "rank": 4, "share": 0.0 }, { "family": "dense_gemm", "rank": 4, "share": 0.0 } ], "mean_shares": { "attention": 0.3911264870692061, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.000268750902798599, "moe_gemm": 0.5660210180238645, "moe_router": 0.004378996059032046, "norm_elementwise": 0.02983320960479998, "sampler": 0.0 }, "reason": "classifiability, representativeness, or recovery gate failed", "run_id": "P03-C00-saturation", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 2, "windows": [ { "attention_subshares": { "attention_decode": 0.15040135314337208, "attention_mixed": 0.28933706610779675, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9918450008730845, "mode_shares": { "FULL": { "attention": 0.6859966420485143, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0019314646391670124, "moe_gemm": 0.2659878061842072, "moe_router": 0.012555897863413516, "norm_elementwise": 0.025494810657793975, "sampler": 0.0 }, "NONE": { "attention": 0.3425246256579563, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6147373284349258, "moe_router": 0.003205686402689487, "norm_elementwise": 0.030942924035345834, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.61102927558752, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0013975676747442667, "moe_gemm": 0.3571425323248457, "moe_router": 0.006697455630309823, "norm_elementwise": 0.018973805351208753, "sampler": 0.0 } }, "mode_steps": { "FULL": 6, "NONE": 1, "PIECEWISE": 1 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5172566828279285 }, { "family": "attention", "rank": 2, "share": 0.4397384192511688 }, { "family": "norm_elementwise", "rank": 3, "share": 0.028771804175374255 }, { "family": "moe_router", "rank": 4, "share": 0.0055405928130157975 }, { "family": "kv_memory", "rank": 4, "share": 0.000537501805597198 }, { "family": "collective", "rank": 4, "share": 0.0 }, { "family": "sampler", "rank": 4, "share": 0.0 }, { "family": "dense_gemm", "rank": 4, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 1.22313193325346, "mode_FULL": 0.7720860330486908, "mode_NONE": -1.155709946053278, "mode_PIECEWISE": 0.5, "prefill_fraction": -0.8564873113454512, "scheduled_tokens": -1.021286605051562 }, "valid": false }, "shares": { "attention": 0.4397384192511688, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.000537501805597198, "moe_gemm": 0.5172566828279285, "moe_router": 0.0055405928130157975, "norm_elementwise": 0.028771804175374255, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 2966.5110000000122, "name": "triton_poi_fused_3" }, { "duration_us": 1605.9449999999956, "name": "triton_red_fused_2" }, { "duration_us": 1552.6929999999936, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 63.32699999999999, "name": "triton_poi_fused_2" }, { "duration_us": 34.559000000000005, "name": "triton_red_fused_1" }, { "duration_us": 28.895999999999994, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 11.679, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.3425145548872434, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9914119224463182, "mode_shares": { "NONE": { "attention": 0.3425145548872434, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6147853532198007, "moe_router": 0.0032173993050482958, "norm_elementwise": 0.030894615034225702, "sampler": 0.0 } }, "mode_steps": { "NONE": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.6147853532198007 }, { "family": "attention", "rank": 2, "share": 0.3425145548872434 }, { "family": "norm_elementwise", "rank": 3, "share": 0.030894615034225702 }, { "family": "moe_router", "rank": 4, "share": 0.0032173993050482958 }, { "family": "collective", "rank": 4, "share": 0.0 }, { "family": "sampler", "rank": 4, "share": 0.0 }, { "family": "dense_gemm", "rank": 4, "share": 0.0 }, { "family": "kv_memory", "rank": 4, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -1.5373920998057986, "mode_FULL": -1.1124192104801658, "mode_NONE": 1.1124192104801658, "mode_PIECEWISE": 0.0, "prefill_fraction": 1.1145676479021394, "scheduled_tokens": 1.1485324061566928 }, "valid": false }, "shares": { "attention": 0.3425145548872434, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6147853532198007, "moe_router": 0.0032173993050482958, "norm_elementwise": 0.030894615034225702, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 17168.532999999996, "name": "triton_poi_fused_3" }, { "duration_us": 8516.018999999993, "name": "triton_red_fused_2" }, { "duration_us": 7858.939000000003, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 365.792, "name": "triton_poi_fused_2" }, { "duration_us": 181.474, "name": "triton_red_fused_1" }, { "duration_us": 107.04, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 12.894999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 2 } ] } }, "P04": { "moderate": { "mean_ranking": [ { "family": "attention", "rank": 1, "share": 0.47883668691193637 }, { "family": "moe_gemm", "rank": 2, "share": 0.4063754056124169 }, { "family": "norm_elementwise", "rank": 3, "share": 0.05854649280424695 }, { "family": "moe_router", "rank": 4, "share": 0.0327989475272124 }, { "family": "kv_memory", "rank": 5, "share": 0.004481485009351725 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "mean_shares": { "attention": 0.47883668691193637, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004481485009351725, "moe_gemm": 0.4063754056124169, "moe_router": 0.0327989475272124, "norm_elementwise": 0.05854649280424695, "sampler": 0.0 }, "reason": null, "run_id": "P04-C00-moderate", "status": "EVALUABLE", "valid_window_count": 2, "window_count": 2, "windows": [ { "attention_subshares": { "attention_decode": 0.45337846230845036, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9811078968569179, "mode_shares": { "FULL": { "attention": 0.45337846230845036, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.00447249169315189, "moe_gemm": 0.4320822710822647, "moe_router": 0.03260980879841117, "norm_elementwise": 0.05856486297463963, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "attention", "rank": 1, "share": 0.45337846230845036 }, { "family": "moe_gemm", "rank": 2, "share": 0.4320822710822647 }, { "family": "norm_elementwise", "rank": 3, "share": 0.05856486297463963 }, { "family": "moe_router", "rank": 4, "share": 0.03260980879841117 }, { "family": "kv_memory", "rank": 5, "share": 0.00447249169315189 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 0.20844725339793926, "mode_FULL": 0.18226661968758462, "mode_NONE": -0.18226661968758412, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.15943564286260098, "scheduled_tokens": -0.15585724120282418 }, "valid": true }, "shares": { "attention": 0.45337846230845036, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.00447249169315189, "moe_gemm": 0.4320822710822647, "moe_router": 0.03260980879841117, "norm_elementwise": 0.05856486297463963, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 600.4589999999997, "name": "triton_poi_fused_3" }, { "duration_us": 503.8849999999992, "name": "triton_red_fused_2" }, { "duration_us": 467.6160000000004, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 19.391000000000002, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 12.958999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 11.197999999999999, "name": "triton_red_fused_1" }, { "duration_us": 9.726999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": true, "window": 1 }, { "attention_subshares": { "attention_decode": 0.5042949115154224, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.980970138873411, "mode_shares": { "FULL": { "attention": 0.5042949115154224, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004490478325551558, "moe_gemm": 0.3806685401425692, "moe_router": 0.032988086256013634, "norm_elementwise": 0.058528122633854276, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "attention", "rank": 1, "share": 0.5042949115154224 }, { "family": "moe_gemm", "rank": 2, "share": 0.3806685401425692 }, { "family": "norm_elementwise", "rank": 3, "share": 0.058528122633854276 }, { "family": "moe_router", "rank": 4, "share": 0.032988086256013634 }, { "family": "kv_memory", "rank": 5, "share": 0.004490478325551558 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 0.20844725339793926, "mode_FULL": 0.18226661968758462, "mode_NONE": -0.18226661968758412, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.15943564286260098, "scheduled_tokens": -0.15585724120282418 }, "valid": true }, "shares": { "attention": 0.5042949115154224, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004490478325551558, "moe_gemm": 0.3806685401425692, "moe_router": 0.032988086256013634, "norm_elementwise": 0.058528122633854276, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 600.0620000000005, "name": "triton_poi_fused_3" }, { "duration_us": 501.89399999999864, "name": "triton_red_fused_2" }, { "duration_us": 467.97200000000095, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 19.328, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 12.800999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 11.870999999999999, "name": "triton_red_fused_1" }, { "duration_us": 10.014999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": true, "window": 2 } ] }, "saturation": { "mean_ranking": [ { "family": "attention", "rank": 1, "share": 0.6587659578842232 }, { "family": "moe_gemm", "rank": 2, "share": 0.29774483506191735 }, { "family": "norm_elementwise", "rank": 3, "share": 0.022973020262564953 }, { "family": "moe_router", "rank": 4, "share": 0.011567306064400342 }, { "family": "kv_memory", "rank": 4, "share": 0.0017453967614688727 }, { "family": "collective", "rank": 6, "share": 0.0 }, { "family": "sampler", "rank": 6, "share": 0.0 }, { "family": "dense_gemm", "rank": 6, "share": 0.0 } ], "mean_shares": { "attention": 0.6587659578842232, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0017453967614688727, "moe_gemm": 0.29774483506191735, "moe_router": 0.011567306064400342, "norm_elementwise": 0.022973020262564953, "sampler": 0.0 }, "reason": "classifiability, representativeness, or recovery gate failed", "run_id": "P04-C00-saturation", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 2, "windows": [ { "attention_subshares": { "attention_decode": 0.6545383651006825, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.992872517456777, "mode_shares": { "FULL": { "attention": 0.6545383651006825, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001725224109977307, "moe_gemm": 0.30244289390345225, "moe_router": 0.011446277854389742, "norm_elementwise": 0.022719756488275074, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "attention", "rank": 1, "share": 0.6545383651006825 }, { "family": "moe_gemm", "rank": 2, "share": 0.30244289390345225 }, { "family": "norm_elementwise", "rank": 3, "share": 0.022719756488275074 }, { "family": "moe_router", "rank": 4, "share": 0.011446277854389742 }, { "family": "kv_memory", "rank": 4, "share": 0.001725224109977307 }, { "family": "collective", "rank": 6, "share": 0.0 }, { "family": "sampler", "rank": 6, "share": 0.0 }, { "family": "dense_gemm", "rank": 6, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -2.090753569627607, "mode_FULL": 0.3444176950404237, "mode_NONE": -0.3444176950404235, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.3279408074303144, "scheduled_tokens": -0.3384806476596461 }, "valid": false }, "shares": { "attention": 0.6545383651006825, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001725224109977307, "moe_gemm": 0.30244289390345225, "moe_router": 0.011446277854389742, "norm_elementwise": 0.022719756488275074, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 702.7299999999998, "name": "triton_poi_fused_3" }, { "duration_us": 538.8529999999995, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 511.6859999999996, "name": "triton_red_fused_2" }, { "duration_us": 20.480999999999998, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.599, "name": "triton_poi_fused_2" }, { "duration_us": 11.903999999999998, "name": "triton_red_fused_1" }, { "duration_us": 10.879999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.6629935506677639, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9927205146123725, "mode_shares": { "FULL": { "attention": 0.6629935506677639, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0017655694129604385, "moe_gemm": 0.29304677622038244, "moe_router": 0.01168833427441094, "norm_elementwise": 0.02322628403685483, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "attention", "rank": 1, "share": 0.6629935506677639 }, { "family": "moe_gemm", "rank": 2, "share": 0.29304677622038244 }, { "family": "norm_elementwise", "rank": 3, "share": 0.02322628403685483 }, { "family": "moe_router", "rank": 4, "share": 0.01168833427441094 }, { "family": "kv_memory", "rank": 4, "share": 0.0017655694129604385 }, { "family": "collective", "rank": 6, "share": 0.0 }, { "family": "sampler", "rank": 6, "share": 0.0 }, { "family": "dense_gemm", "rank": 6, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -3.0407898355557177, "mode_FULL": 0.3444176950404237, "mode_NONE": -0.3444176950404235, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.3279408074303144, "scheduled_tokens": -0.3392815338864717 }, "valid": false }, "shares": { "attention": 0.6629935506677639, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0017655694129604385, "moe_gemm": 0.29304677622038244, "moe_router": 0.01168833427441094, "norm_elementwise": 0.02322628403685483, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 697.0249999999994, "name": "triton_poi_fused_3" }, { "duration_us": 539.4639999999994, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 512.0369999999991, "name": "triton_red_fused_2" }, { "duration_us": 20.703, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.440999999999999, "name": "triton_poi_fused_2" }, { "duration_us": 11.392999999999999, "name": "triton_red_fused_1" }, { "duration_us": 11.231999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 2 } ] } }, "P05": { "moderate": { "mean_ranking": null, "mean_shares": null, "reason": "pattern/config cell missing under A-P3-7", "run_id": "P05-C00-moderate", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 0, "windows": [] }, "saturation": { "mean_ranking": null, "mean_shares": null, "reason": "pattern/config cell missing under A-P3-7", "run_id": "P05-C00-saturation", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 0, "windows": [] } }, "P06": { "moderate": { "mean_ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.575196967256715 }, { "family": "attention", "rank": 2, "share": 0.3159632048695007 }, { "family": "norm_elementwise", "rank": 3, "share": 0.05688419362270496 }, { "family": "moe_router", "rank": 4, "share": 0.02969053707107777 }, { "family": "kv_memory", "rank": 5, "share": 0.004277410164380805 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "mean_shares": { "attention": 0.3159632048695007, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004277410164380805, "moe_gemm": 0.575196967256715, "moe_router": 0.02969053707107777, "norm_elementwise": 0.05688419362270496, "sampler": 0.0 }, "reason": "classifiability, representativeness, or recovery gate failed", "run_id": "P06-C00-moderate", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 2, "windows": [ { "attention_subshares": { "attention_decode": 0.2490290455613554, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9782676099166654, "mode_shares": { "FULL": { "attention": 0.2490290455613554, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.005145523506508112, "moe_gemm": 0.6200403635488907, "moe_router": 0.03550127037050399, "norm_elementwise": 0.06855140692940716, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.6200403635488907 }, { "family": "attention", "rank": 2, "share": 0.2490290455613554 }, { "family": "norm_elementwise", "rank": 3, "share": 0.06855140692940716 }, { "family": "moe_router", "rank": 4, "share": 0.03550127037050399 }, { "family": "kv_memory", "rank": 5, "share": 0.005145523506508112 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -0.7216535064826213, "mode_FULL": 0.13539969781837916, "mode_NONE": -0.1341287527105229, "mode_PIECEWISE": -0.018343220956176326, "prefill_fraction": -0.13284443594178524, "scheduled_tokens": -0.12475886497271786 }, "valid": false }, "shares": { "attention": 0.2490290455613554, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.005145523506508112, "moe_gemm": 0.6200403635488907, "moe_router": 0.03550127037050399, "norm_elementwise": 0.06855140692940716, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 597.553, "name": "triton_poi_fused_3" }, { "duration_us": 503.07699999999915, "name": "triton_red_fused_2" }, { "duration_us": 466.9400000000012, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 19.869999999999997, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.854, "name": "triton_poi_fused_2" }, { "duration_us": 11.744, "name": "triton_red_fused_1" }, { "duration_us": 9.727, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.382897364177646, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9857570160520932, "mode_shares": { "FULL": { "attention": 0.382897364177646, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003409296822253497, "moe_gemm": 0.5303535709645394, "moe_router": 0.023879803771651553, "norm_elementwise": 0.04521698031600275, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5303535709645394 }, { "family": "attention", "rank": 2, "share": 0.382897364177646 }, { "family": "norm_elementwise", "rank": 3, "share": 0.04521698031600275 }, { "family": "moe_router", "rank": 4, "share": 0.023879803771651553 }, { "family": "kv_memory", "rank": 5, "share": 0.003409296822253497 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 2.7828468550637027, "mode_FULL": 0.13539969781837916, "mode_NONE": -0.1341287527105229, "mode_PIECEWISE": -0.018343220956176326, "prefill_fraction": -0.13284443594178524, "scheduled_tokens": -0.10682572566427663 }, "valid": false }, "shares": { "attention": 0.382897364177646, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003409296822253497, "moe_gemm": 0.5303535709645394, "moe_router": 0.023879803771651553, "norm_elementwise": 0.04521698031600275, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 620.7480000000002, "name": "triton_poi_fused_3" }, { "duration_us": 515.2009999999995, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 493.54399999999913, "name": "triton_red_fused_2" }, { "duration_us": 19.936, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.312, "name": "triton_poi_fused_2" }, { "duration_us": 10.751999999999999, "name": "triton_red_fused_1" }, { "duration_us": 10.4, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 2 } ] }, "saturation": { "mean_ranking": [ { "family": "attention", "rank": 1, "share": 0.5658804400108743 }, { "family": "moe_gemm", "rank": 2, "share": 0.3934686862786809 }, { "family": "norm_elementwise", "rank": 3, "share": 0.022493433009649746 }, { "family": "moe_router", "rank": 4, "share": 0.010415454290445056 }, { "family": "kv_memory", "rank": 4, "share": 0.0015415313949460807 }, { "family": "collective", "rank": 6, "share": 0.0 }, { "family": "sampler", "rank": 6, "share": 0.0 }, { "family": "dense_gemm", "rank": 6, "share": 0.0 } ], "mean_shares": { "attention": 0.5658804400108743, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0015415313949460807, "moe_gemm": 0.3934686862786809, "moe_router": 0.010415454290445056, "norm_elementwise": 0.022493433009649746, "sampler": 0.0 }, "reason": "classifiability, representativeness, or recovery gate failed", "run_id": "P06-C00-saturation", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 2, "windows": [ { "attention_subshares": { "attention_decode": 0.5606386878931048, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9937049249586525, "mode_shares": { "FULL": { "attention": 0.5606386878931048, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0015728835856848925, "moe_gemm": 0.3985345690982096, "moe_router": 0.010374903112678729, "norm_elementwise": 0.022583881268974364, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "attention", "rank": 1, "share": 0.5606386878931048 }, { "family": "moe_gemm", "rank": 2, "share": 0.3985345690982096 }, { "family": "norm_elementwise", "rank": 3, "share": 0.022583881268974364 }, { "family": "moe_router", "rank": 4, "share": 0.010374903112678729 }, { "family": "kv_memory", "rank": 4, "share": 0.0015728835856848925 }, { "family": "collective", "rank": 6, "share": 0.0 }, { "family": "sampler", "rank": 6, "share": 0.0 }, { "family": "dense_gemm", "rank": 6, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -0.19939502094061695, "mode_FULL": 0.3784962133407253, "mode_NONE": -0.3784962133407256, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.34967744618584184, "scheduled_tokens": -0.3730920628084988 }, "valid": false }, "shares": { "attention": 0.5606386878931048, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0015728835856848925, "moe_gemm": 0.3985345690982096, "moe_router": 0.010374903112678729, "norm_elementwise": 0.022583881268974364, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 730.718, "name": "triton_poi_fused_3" }, { "duration_us": 532.1659999999997, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 517.7589999999993, "name": "triton_red_fused_2" }, { "duration_us": 22.624, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 14.944999999999999, "name": "triton_poi_fused_2" }, { "duration_us": 12.351999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 11.359999999999998, "name": "triton_red_fused_1" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.5711221921286438, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9938941650105397, "mode_shares": { "FULL": { "attention": 0.5711221921286438, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001510179204207269, "moe_gemm": 0.3884028034591522, "moe_router": 0.010456005468211384, "norm_elementwise": 0.022402984750325126, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "attention", "rank": 1, "share": 0.5711221921286438 }, { "family": "moe_gemm", "rank": 2, "share": 0.3884028034591522 }, { "family": "norm_elementwise", "rank": 3, "share": 0.022402984750325126 }, { "family": "moe_router", "rank": 4, "share": 0.010456005468211384 }, { "family": "kv_memory", "rank": 4, "share": 0.001510179204207269 }, { "family": "collective", "rank": 6, "share": 0.0 }, { "family": "sampler", "rank": 6, "share": 0.0 }, { "family": "dense_gemm", "rank": 6, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -3.0651651743014807, "mode_FULL": 0.3784962133407253, "mode_NONE": -0.3784962133407256, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.34967744618584184, "scheduled_tokens": -0.381504751465261 }, "valid": false }, "shares": { "attention": 0.5711221921286438, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001510179204207269, "moe_gemm": 0.3884028034591522, "moe_router": 0.010456005468211384, "norm_elementwise": 0.022402984750325126, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 735.0089999999993, "name": "triton_poi_fused_3" }, { "duration_us": 530.0759999999996, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 511.90599999999927, "name": "triton_red_fused_2" }, { "duration_us": 21.855999999999995, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 15.872, "name": "triton_poi_fused_2" }, { "duration_us": 11.360999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 10.878999999999998, "name": "triton_red_fused_1" } ], "valid": false, "window": 2 } ] } }, "P07": { "moderate": { "mean_ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.62183214684387 }, { "family": "attention", "rank": 2, "share": 0.28668399704125846 }, { "family": "norm_elementwise", "rank": 3, "share": 0.04862705270918968 }, { "family": "moe_router", "rank": 4, "share": 0.024198716148019384 }, { "family": "kv_memory", "rank": 5, "share": 0.003722036909265734 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "mean_shares": { "attention": 0.28668399704125846, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003722036909265734, "moe_gemm": 0.62183214684387, "moe_router": 0.024198716148019384, "norm_elementwise": 0.04862705270918968, "sampler": 0.0 }, "reason": "classifiability, representativeness, or recovery gate failed", "run_id": "P07-C00-moderate", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 2, "windows": [ { "attention_subshares": { "attention_decode": 0.306761436001029, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9841089106220091, "mode_shares": { "FULL": { "attention": 0.306761436001029, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003944802403864725, "moe_gemm": 0.5964090291561805, "moe_router": 0.02562456323133302, "norm_elementwise": 0.051369079829601885, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5964090291561805 }, { "family": "attention", "rank": 2, "share": 0.306761436001029 }, { "family": "norm_elementwise", "rank": 3, "share": 0.051369079829601885 }, { "family": "moe_router", "rank": 4, "share": 0.02562456323133302 }, { "family": "kv_memory", "rank": 5, "share": 0.003944802403864725 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -0.18368608035893982, "mode_FULL": 0.1535286967084372, "mode_NONE": -0.15352869670843752, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.1535266720575854, "scheduled_tokens": -0.13391206652423035 }, "valid": true }, "shares": { "attention": 0.306761436001029, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003944802403864725, "moe_gemm": 0.5964090291561805, "moe_router": 0.02562456323133302, "norm_elementwise": 0.051369079829601885, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 606.694, "name": "triton_poi_fused_3" }, { "duration_us": 538.9419999999992, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 496.9549999999989, "name": "triton_red_fused_2" }, { "duration_us": 20.128, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 15.04, "name": "triton_poi_fused_2" }, { "duration_us": 10.56, "name": "triton_red_fused_1" }, { "duration_us": 10.304, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.2666065580814879, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9860189886811974, "mode_shares": { "FULL": { "attention": 0.2666065580814879, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0034992714146667428, "moe_gemm": 0.6472552645315595, "moe_router": 0.02277286906470575, "norm_elementwise": 0.04588502558877749, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.6472552645315595 }, { "family": "attention", "rank": 2, "share": 0.2666065580814879 }, { "family": "norm_elementwise", "rank": 3, "share": 0.04588502558877749 }, { "family": "moe_router", "rank": 4, "share": 0.02277286906470575 }, { "family": "kv_memory", "rank": 5, "share": 0.0034992714146667428 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 3.069910871828644, "mode_FULL": 0.1535286967084372, "mode_NONE": -0.15352869670843752, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.1535266720575854, "scheduled_tokens": -0.11608746652035899 }, "valid": false }, "shares": { "attention": 0.2666065580814879, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0034992714146667428, "moe_gemm": 0.6472552645315595, "moe_router": 0.02277286906470575, "norm_elementwise": 0.04588502558877749, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 621.5659999999995, "name": "triton_poi_fused_3" }, { "duration_us": 529.2479999999987, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 510.27699999999976, "name": "triton_red_fused_2" }, { "duration_us": 20.607000000000003, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.184, "name": "triton_poi_fused_2" }, { "duration_us": 11.230999999999998, "name": "triton_red_fused_1" }, { "duration_us": 10.817, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 2 } ] }, "saturation": { "mean_ranking": null, "mean_shares": null, "reason": "accepted trace windows 0/2", "run_id": "P07-C00-saturation", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 0, "windows": [] } }, "P08": { "moderate": { "mean_ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5706435605086021 }, { "family": "attention", "rank": 2, "share": 0.34593945846402396 }, { "family": "norm_elementwise", "rank": 3, "share": 0.04440163968760805 }, { "family": "moe_router", "rank": 4, "share": 0.022174807436130248 }, { "family": "kv_memory", "rank": 5, "share": 0.0034157188029328364 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "mean_shares": { "attention": 0.34593945846402396, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0034157188029328364, "moe_gemm": 0.5706435605086021, "moe_router": 0.022174807436130248, "norm_elementwise": 0.04440163968760805, "sampler": 0.0 }, "reason": "classifiability, representativeness, or recovery gate failed", "run_id": "P08-C00-moderate", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 2, "windows": [ { "attention_subshares": { "attention_decode": 0.3248872069635257, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9877052895017178, "mode_shares": { "FULL": { "attention": 0.3248872069635257, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0031072028443770152, "moe_gemm": 0.5984635601986847, "moe_router": 0.020260919566213807, "norm_elementwise": 0.04098639992891659, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5984635601986847 }, { "family": "attention", "rank": 2, "share": 0.3248872069635257 }, { "family": "norm_elementwise", "rank": 3, "share": 0.04098639992891659 }, { "family": "moe_router", "rank": 4, "share": 0.020260919566213807 }, { "family": "kv_memory", "rank": 5, "share": 0.0031072028443770152 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 1.0901560791930118, "mode_FULL": 0.16434181266464418, "mode_NONE": -0.16434181266464443, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.16432997461824633, "scheduled_tokens": -0.1413297101061453 }, "valid": false }, "shares": { "attention": 0.3248872069635257, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0031072028443770152, "moe_gemm": 0.5984635601986847, "moe_router": 0.020260919566213807, "norm_elementwise": 0.04098639992891659, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 654.3379999999997, "name": "triton_poi_fused_3" }, { "duration_us": 552.4199999999996, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 513.1979999999996, "name": "triton_red_fused_2" }, { "duration_us": 21.089000000000002, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 14.015999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 12.127999999999998, "name": "triton_red_fused_1" }, { "duration_us": 10.719, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.3669917099645223, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9854450802968766, "mode_shares": { "FULL": { "attention": 0.3669917099645223, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003724234761488658, "moe_gemm": 0.5428235608185195, "moe_router": 0.024088695306046685, "norm_elementwise": 0.04781687944629951, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5428235608185195 }, { "family": "attention", "rank": 2, "share": 0.3669917099645223 }, { "family": "norm_elementwise", "rank": 3, "share": 0.04781687944629951 }, { "family": "moe_router", "rank": 4, "share": 0.024088695306046685 }, { "family": "kv_memory", "rank": 5, "share": 0.003724234761488658 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -1.4164397504981734, "mode_FULL": 0.16434181266464418, "mode_NONE": -0.16434181266464443, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.16432997461824633, "scheduled_tokens": -0.19075947310069616 }, "valid": false }, "shares": { "attention": 0.3669917099645223, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003724234761488658, "moe_gemm": 0.5428235608185195, "moe_router": 0.024088695306046685, "norm_elementwise": 0.04781687944629951, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 632.7909999999997, "name": "triton_poi_fused_3" }, { "duration_us": 540.1919999999998, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 511.9399999999992, "name": "triton_red_fused_2" }, { "duration_us": 20.673000000000002, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.665, "name": "triton_poi_fused_2" }, { "duration_us": 11.713, "name": "triton_red_fused_1" }, { "duration_us": 10.878999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 2 } ] }, "saturation": { "mean_ranking": null, "mean_shares": null, "reason": "accepted trace windows 0/2", "run_id": "P08-C00-saturation", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 0, "windows": [] } }, "P09": { "moderate": { "mean_ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.7499562920571119 }, { "family": "attention", "rank": 2, "share": 0.16190861537800794 }, { "family": "norm_elementwise", "rank": 3, "share": 0.04833573350364303 }, { "family": "moe_router", "rank": 4, "share": 0.021425255352349733 }, { "family": "kv_memory", "rank": 5, "share": 0.0035055829982362854 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "mean_shares": { "attention": 0.16190861537800794, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0035055829982362854, "moe_gemm": 0.7499562920571119, "moe_router": 0.021425255352349733, "norm_elementwise": 0.04833573350364303, "sampler": 0.0 }, "reason": "classifiability, representativeness, or recovery gate failed", "run_id": "P09-C00-moderate", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 2, "windows": [ { "attention_subshares": { "attention_decode": 0.08835627115447606, "attention_mixed": 0.11385037570991731, "attention_prefill": 0.0 }, "classifiable_fraction": 0.988346330660954, "mode_shares": { "FULL": { "attention": 0.280249688903593, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004209638462393143, "moe_gemm": 0.6254634471394533, "moe_router": 0.02523969717175661, "norm_elementwise": 0.0493304218340256, "sampler": 0.0 }, "NONE": { "attention": 0.14806901527656063, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.7989631873012853, "moe_router": 0.006717474937844798, "norm_elementwise": 0.036240204978569675, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.18871401371634564, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0022585830433693877, "moe_gemm": 0.7546316751137306, "moe_router": 0.012749732426996046, "norm_elementwise": 0.031927806640493814, "sampler": 0.0 } }, "mode_steps": { "FULL": 5, "NONE": 1, "PIECEWISE": 2 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.7306681072672004 }, { "family": "attention", "rank": 2, "share": 0.20220664686439338 }, { "family": "norm_elementwise", "rank": 3, "share": 0.039044817770315786 }, { "family": "moe_router", "rank": 4, "share": 0.014406944379520907 }, { "family": "kv_memory", "rank": 5, "share": 0.002019814379523439 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 2.5579606107986748, "mode_FULL": -0.6775421426296558, "mode_NONE": 0.2503307644752007, "mode_PIECEWISE": 0.5907929693818461, "prefill_fraction": 0.6661033678566376, "scheduled_tokens": 0.05206272885676596 }, "valid": false }, "shares": { "attention": 0.20220664686439338, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.002019814379523439, "moe_gemm": 0.7306681072672004, "moe_router": 0.014406944379520907, "norm_elementwise": 0.039044817770315786, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1078.7899999999981, "name": "triton_poi_fused_3" }, { "duration_us": 718.971000000001, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 663.9299999999997, "name": "triton_red_fused_2" }, { "duration_us": 22.880000000000003, "name": "triton_poi_fused_2" }, { "duration_us": 22.017, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 14.112, "name": "triton_red_fused_1" }, { "duration_us": 10.974999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.09568605186600879, "attention_mixed": 0.025924532025613695, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9819166279177437, "mode_shares": { "FULL": { "attention": 0.14040386061386476, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.006289384167983417, "moe_gemm": 0.7278572814656825, "moe_router": 0.03517706269456804, "norm_elementwise": 0.06867748249282202, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.08139719907850929, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0022138539380632135, "moe_gemm": 0.8578037652991323, "moe_router": 0.01403539873195149, "norm_elementwise": 0.033980351851418185, "sampler": 0.0 } }, "mode_steps": { "FULL": 7, "PIECEWISE": 1 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.7692444768470234 }, { "family": "attention", "rank": 2, "share": 0.12161058389162249 }, { "family": "norm_elementwise", "rank": 3, "share": 0.05762664923697027 }, { "family": "moe_router", "rank": 4, "share": 0.028443566325178558 }, { "family": "kv_memory", "rank": 5, "share": 0.004991351616949132 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -0.19954189900373331, "mode_FULL": -0.10469513477046205, "mode_NONE": -0.32861907697425397, "mode_PIECEWISE": 0.29736821980293143, "prefill_fraction": 0.10420387771831544, "scheduled_tokens": -0.23288793337699637 }, "valid": false }, "shares": { "attention": 0.12161058389162249, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004991351616949132, "moe_gemm": 0.7692444768470234, "moe_router": 0.028443566325178558, "norm_elementwise": 0.05762664923697027, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 667.7419999999993, "name": "triton_poi_fused_3" }, { "duration_us": 523.011999999999, "name": "triton_red_fused_2" }, { "duration_us": 498.98300000000086, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 20.736, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 14.591, "name": "triton_poi_fused_2" }, { "duration_us": 11.645, "name": "triton_red_fused_1" }, { "duration_us": 11.36, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 2 } ] }, "saturation": { "mean_ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.6902715167627947 }, { "family": "attention", "rank": 2, "share": 0.26232227513895634 }, { "family": "norm_elementwise", "rank": 3, "share": 0.03432883110553378 }, { "family": "moe_router", "rank": 4, "share": 0.0035556142118645844 }, { "family": "collective", "rank": 4, "share": 0.0 }, { "family": "sampler", "rank": 4, "share": 0.0 }, { "family": "dense_gemm", "rank": 4, "share": 0.0 }, { "family": "kv_memory", "rank": 4, "share": 0.0 } ], "mean_shares": { "attention": 0.26232227513895634, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6902715167627947, "moe_router": 0.0035556142118645844, "norm_elementwise": 0.03432883110553378, "sampler": 0.0 }, "reason": "classifiability, representativeness, or recovery gate failed", "run_id": "P09-C00-saturation", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 2, "windows": [ { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.24676580346741184, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9902796451206958, "mode_shares": { "NONE": { "attention": 0.24676580346741184, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.7048192593007057, "moe_router": 0.0036328436089412205, "norm_elementwise": 0.035061738743637105, "sampler": 0.0 } }, "mode_steps": { "NONE": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.7048192593007057 }, { "family": "attention", "rank": 2, "share": 0.24676580346741184 }, { "family": "norm_elementwise", "rank": 3, "share": 0.035061738743637105 }, { "family": "moe_router", "rank": 4, "share": 0.0036328436089412205 }, { "family": "collective", "rank": 4, "share": 0.0 }, { "family": "sampler", "rank": 4, "share": 0.0 }, { "family": "dense_gemm", "rank": 4, "share": 0.0 }, { "family": "kv_memory", "rank": 4, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 1.259998751515166, "mode_FULL": -1.0890519340869804, "mode_NONE": 1.0890519340869804, "mode_PIECEWISE": 0.0, "prefill_fraction": 1.1263920173520792, "scheduled_tokens": 1.3450157218366598 }, "valid": false }, "shares": { "attention": 0.24676580346741184, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.7048192593007057, "moe_router": 0.0036328436089412205, "norm_elementwise": 0.035061738743637105, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 18507.434, "name": "triton_poi_fused_3" }, { "duration_us": 9166.28299999999, "name": "triton_red_fused_2" }, { "duration_us": 8451.682000000004, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 396.608, "name": "triton_poi_fused_2" }, { "duration_us": 195.36100000000002, "name": "triton_red_fused_1" }, { "duration_us": 75.745, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 15.616, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.27787874681050084, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9906768293176031, "mode_shares": { "NONE": { "attention": 0.27787874681050084, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6757237742248838, "moe_router": 0.0034783848147879478, "norm_elementwise": 0.03359592346743046, "sampler": 0.0 } }, "mode_steps": { "NONE": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.6757237742248838 }, { "family": "attention", "rank": 2, "share": 0.27787874681050084 }, { "family": "norm_elementwise", "rank": 3, "share": 0.03359592346743046 }, { "family": "moe_router", "rank": 4, "share": 0.0034783848147879478 }, { "family": "collective", "rank": 4, "share": 0.0 }, { "family": "sampler", "rank": 4, "share": 0.0 }, { "family": "dense_gemm", "rank": 4, "share": 0.0 }, { "family": "kv_memory", "rank": 4, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -0.2365580579355552, "mode_FULL": -1.0890519340869804, "mode_NONE": 1.0890519340869804, "mode_PIECEWISE": 0.0, "prefill_fraction": 1.1326772391141862, "scheduled_tokens": 1.3450157218366598 }, "valid": false }, "shares": { "attention": 0.27787874681050084, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.6757237742248838, "moe_router": 0.0034783848147879478, "norm_elementwise": 0.03359592346743046, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 18504.999000000003, "name": "triton_poi_fused_3" }, { "duration_us": 9192.093999999992, "name": "triton_red_fused_2" }, { "duration_us": 8458.98800000001, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 398.754, "name": "triton_poi_fused_2" }, { "duration_us": 195.68099999999998, "name": "triton_red_fused_1" }, { "duration_us": 84.479, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 15.392, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 2 } ] } }, "P10": { "moderate": { "mean_ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5404178421352701 }, { "family": "attention", "rank": 2, "share": 0.3060614779541131 }, { "family": "norm_elementwise", "rank": 3, "share": 0.09802642887199953 }, { "family": "moe_router", "rank": 4, "share": 0.02813772466138177 }, { "family": "kv_memory", "rank": 5, "share": 0.006793424317425972 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "mean_shares": { "attention": 0.3060614779541131, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.006793424317425972, "moe_gemm": 0.5404178421352701, "moe_router": 0.02813772466138177, "norm_elementwise": 0.09802642887199953, "sampler": 0.0 }, "reason": "classifiability, representativeness, or recovery gate failed", "run_id": "P10-C00-moderate", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 2, "windows": [ { "attention_subshares": { "attention_decode": 0.3087850643091725, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.985252225101006, "mode_shares": { "FULL": { "attention": 0.3087850643091725, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.005163136163815447, "moe_gemm": 0.5777999387887653, "moe_router": 0.02008575072504131, "norm_elementwise": 0.07341833511421153, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5777999387887653 }, { "family": "attention", "rank": 2, "share": 0.3087850643091725 }, { "family": "norm_elementwise", "rank": 3, "share": 0.07341833511421153 }, { "family": "moe_router", "rank": 4, "share": 0.02008575072504131 }, { "family": "kv_memory", "rank": 5, "share": 0.005163136163815447 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 4.655696267017126, "mode_FULL": 0.17677689026422408, "mode_NONE": -0.1682723158645361, "mode_PIECEWISE": -0.05341411394958018, "prefill_fraction": -0.12905587442539998, "scheduled_tokens": -0.09951290348812954 }, "valid": false }, "shares": { "attention": 0.3087850643091725, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.005163136163815447, "moe_gemm": 0.5777999387887653, "moe_router": 0.02008575072504131, "norm_elementwise": 0.07341833511421153, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 583.5649999999997, "name": "triton_poi_fused_3" }, { "duration_us": 466.8209999999995, "name": "triton_red_fused_2" }, { "duration_us": 19.617, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.536, "name": "triton_poi_fused_2" }, { "duration_us": 11.231999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 10.049, "name": "triton_red_fused_1" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.3033378915990537, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9736215707793747, "mode_shares": { "FULL": { "attention": 0.3033378915990537, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.008423712471036498, "moe_gemm": 0.5030357454817748, "moe_router": 0.03618969859772223, "norm_elementwise": 0.12263452262978754, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5030357454817748 }, { "family": "attention", "rank": 2, "share": 0.3033378915990537 }, { "family": "norm_elementwise", "rank": 3, "share": 0.12263452262978754 }, { "family": "moe_router", "rank": 4, "share": 0.03618969859772223 }, { "family": "kv_memory", "rank": 5, "share": 0.008423712471036498 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -0.5055344205281964, "mode_FULL": 0.17677689026422408, "mode_NONE": -0.1682723158645361, "mode_PIECEWISE": -0.05341411394958018, "prefill_fraction": -0.12905587442539998, "scheduled_tokens": -0.10506250419671144 }, "valid": false }, "shares": { "attention": 0.3033378915990537, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.008423712471036498, "moe_gemm": 0.5030357454817748, "moe_router": 0.03618969859772223, "norm_elementwise": 0.12263452262978754, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 590.9459999999992, "name": "triton_poi_fused_3" }, { "duration_us": 467.6929999999989, "name": "triton_red_fused_2" }, { "duration_us": 18.272, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.152, "name": "triton_poi_fused_2" }, { "duration_us": 9.63, "name": "triton_red_fused_1" } ], "valid": false, "window": 2 } ] }, "saturation": { "mean_ranking": [ { "family": "attention", "rank": 1, "share": 0.6779796330559141 }, { "family": "moe_gemm", "rank": 2, "share": 0.2890057629595925 }, { "family": "norm_elementwise", "rank": 3, "share": 0.01871664375594286 }, { "family": "moe_router", "rank": 4, "share": 0.007610719195516601 }, { "family": "kv_memory", "rank": 4, "share": 0.0009838772120851383 }, { "family": "collective", "rank": 4, "share": 0.0 }, { "family": "sampler", "rank": 4, "share": 0.0 }, { "family": "dense_gemm", "rank": 4, "share": 0.0 } ], "mean_shares": { "attention": 0.6779796330559141, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0009838772120851383, "moe_gemm": 0.2890057629595925, "moe_router": 0.007610719195516601, "norm_elementwise": 0.01871664375594286, "sampler": 0.0 }, "reason": "classifiability, representativeness, or recovery gate failed", "run_id": "P10-C00-saturation", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 2, "windows": [ { "attention_subshares": { "attention_decode": 0.7471257503417844, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9942106688319626, "mode_shares": { "FULL": { "attention": 0.7471257503417844, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0013626029325187864, "moe_gemm": 0.21782046124566493, "moe_router": 0.009663599861937516, "norm_elementwise": 0.01823825445005707, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "attention", "rank": 1, "share": 0.7471257503417844 }, { "family": "moe_gemm", "rank": 2, "share": 0.21782046124566493 }, { "family": "norm_elementwise", "rank": 3, "share": 0.01823825445005707 }, { "family": "moe_router", "rank": 3, "share": 0.009663599861937516 }, { "family": "kv_memory", "rank": 5, "share": 0.0013626029325187864 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 3.613259323224499, "mode_FULL": 0.6120018940246724, "mode_NONE": -0.5981417765928579, "mode_PIECEWISE": -0.10976470169608525, "prefill_fraction": -0.6117521895228502, "scheduled_tokens": -0.5755060211990467 }, "valid": false }, "shares": { "attention": 0.7471257503417844, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0013626029325187864, "moe_gemm": 0.21782046124566493, "moe_router": 0.009663599861937516, "norm_elementwise": 0.01823825445005707, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 637.9129999999991, "name": "triton_poi_fused_3" }, { "duration_us": 513.3399999999995, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 484.63699999999847, "name": "triton_red_fused_2" }, { "duration_us": 19.874, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.408, "name": "triton_poi_fused_2" }, { "duration_us": 10.879999999999999, "name": "triton_red_fused_1" }, { "duration_us": 10.305, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.2679713777414123, "attention_mixed": 0.3408621380286316, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9943826035261398, "mode_shares": { "FULL": { "attention": 0.6506807095871076, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.001469412163770193, "moe_gemm": 0.3120351814822058, "moe_router": 0.01012812440986268, "norm_elementwise": 0.0195308311121687, "sampler": 0.0 }, "NONE": { "attention": 0.5795322961533458, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.39390960062584945, "moe_router": 0.0023577446138654075, "norm_elementwise": 0.01895990875545615, "sampler": 0.0 } }, "mode_steps": { "FULL": 7, "NONE": 1 }, "ranking": [ { "family": "attention", "rank": 1, "share": 0.6088335157700439 }, { "family": "moe_gemm", "rank": 2, "share": 0.36019106467352013 }, { "family": "norm_elementwise", "rank": 3, "share": 0.019195033061828647 }, { "family": "moe_router", "rank": 4, "share": 0.005557838529095687 }, { "family": "kv_memory", "rank": 4, "share": 0.0006051514916514902 }, { "family": "collective", "rank": 4, "share": 0.0 }, { "family": "sampler", "rank": 4, "share": 0.0 }, { "family": "dense_gemm", "rank": 4, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 28.040640400381754, "mode_FULL": 0.09182576274871186, "mode_NONE": -0.07574082366962798, "mode_PIECEWISE": -0.10976470169608525, "prefill_fraction": -0.09431170009009414, "scheduled_tokens": -0.3287773474224777 }, "valid": false }, "shares": { "attention": 0.6088335157700439, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0006051514916514902, "moe_gemm": 0.36019106467352013, "moe_router": 0.005557838529095687, "norm_elementwise": 0.019195033061828647, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1568.3549999999968, "name": "triton_poi_fused_3" }, { "duration_us": 937.5360000000019, "name": "triton_red_fused_2" }, { "duration_us": 870.9730000000023, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 32.38400000000001, "name": "triton_poi_fused_2" }, { "duration_us": 25.343999999999998, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 21.376, "name": "triton_red_fused_1" }, { "duration_us": 11.167999999999997, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 2 } ] } }, "P11": { "moderate": { "mean_ranking": null, "mean_shares": null, "reason": "pattern/config cell missing under A-P3-7", "run_id": "P11-C00-moderate", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 0, "windows": [] }, "saturation": { "mean_ranking": null, "mean_shares": null, "reason": "pattern/config cell missing under A-P3-7", "run_id": "P11-C00-saturation", "status": "NOT_EVALUABLE", "valid_window_count": 0, "window_count": 0, "windows": [] } } }, "operator_windows": { "P01-C00-moderate": [ { "attention_subshares": { "attention_decode": 0.0, "attention_mixed": 0.11987238161795156, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9905881019946707, "mode_shares": { "NONE": { "attention": 0.1007462687465188, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8471040152242396, "moe_router": 0.008477215998495907, "norm_elementwise": 0.034119643236757626, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.13605518456441312, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0019444790834074754, "moe_gemm": 0.8102627123318585, "moe_router": 0.01080794700368473, "norm_elementwise": 0.03163704570787867, "sampler": 0.0 } }, "mode_steps": { "NONE": 3, "PIECEWISE": 5 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.8271478398184453 }, { "family": "attention", "rank": 2, "share": 0.11987238161795156 }, { "family": "norm_elementwise", "rank": 3, "share": 0.032774871259148075 }, { "family": "moe_router", "rank": 4, "share": 0.009739725006365179 }, { "family": "kv_memory", "rank": 4, "share": 0.0010532842927605177 }, { "family": "collective", "rank": 4, "share": 0.0 }, { "family": "sampler", "rank": 4, "share": 0.0 }, { "family": "dense_gemm", "rank": 4, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 2.4721524781047854, "mode_FULL": -0.2325584995849942, "mode_NONE": 0.3041456447839143, "mode_PIECEWISE": -0.24468169875030038, "prefill_fraction": 0.18099057277285577, "scheduled_tokens": 0.4474608400278538 }, "valid": false }, "shares": { "attention": 0.11987238161795156, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0010532842927605177, "moe_gemm": 0.8271478398184453, "moe_router": 0.009739725006365179, "norm_elementwise": 0.032774871259148075, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1567.9510000000005, "name": "triton_poi_fused_3" }, { "duration_us": 933.1070000000002, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 827.689, "name": "triton_red_fused_2" }, { "duration_us": 33.057, "name": "triton_poi_fused_2" }, { "duration_us": 22.368999999999996, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 17.247, "name": "triton_red_fused_1" }, { "duration_us": 11.647999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.008867955248024707, "attention_mixed": 0.11302508576620553, "attention_prefill": 0.0 }, "classifiable_fraction": 0.990127660582764, "mode_shares": { "FULL": { "attention": 0.16315875281832684, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0031741793017298413, "moe_gemm": 0.7536332801624461, "moe_router": 0.02179864485086512, "norm_elementwise": 0.045434533244984684, "sampler": 0.0 }, "NONE": { "attention": 0.09828250109360281, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.8488043657595763, "moe_router": 0.008302816259724543, "norm_elementwise": 0.0348733229605455, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.1472178594517614, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.002166218689199354, "moe_gemm": 0.7946960932441856, "moe_router": 0.012792489660640699, "norm_elementwise": 0.033466283510587794, "sampler": 0.0 } }, "mode_steps": { "FULL": 1, "NONE": 3, "PIECEWISE": 4 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.8214241451495896 }, { "family": "attention", "rank": 2, "share": 0.12189304101423025 }, { "family": "norm_elementwise", "rank": 3, "share": 0.034869855313022065 }, { "family": "moe_router", "rank": 4, "share": 0.010879021850869232 }, { "family": "kv_memory", "rank": 4, "share": 0.0010615972550528194 }, { "family": "collective", "rank": 6, "share": 0.0 }, { "family": "sampler", "rank": 6, "share": 0.0 }, { "family": "dense_gemm", "rank": 6, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 1.4422983740600546, "mode_FULL": 0.3594518697735859, "mode_NONE": 0.3041456447839143, "mode_PIECEWISE": -0.49598146699059914, "prefill_fraction": -0.3699982864929203, "scheduled_tokens": 0.1504241077629697 }, "valid": false }, "shares": { "attention": 0.12189304101423025, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0010615972550528194, "moe_gemm": 0.8214241451495896, "moe_router": 0.010879021850869232, "norm_elementwise": 0.034869855313022065, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1449.5139999999994, "name": "triton_poi_fused_3" }, { "duration_us": 884.6050000000004, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 826.8859999999994, "name": "triton_red_fused_2" }, { "duration_us": 30.943000000000005, "name": "triton_poi_fused_2" }, { "duration_us": 22.431999999999995, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 17.441, "name": "triton_red_fused_1" }, { "duration_us": 11.328999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 2 } ], "P02-C00-moderate": [ { "attention_subshares": { "attention_decode": 0.16431648329180198, "attention_mixed": 0.040375747240313245, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9899496306808163, "mode_shares": { "FULL": { "attention": 0.2070416346282377, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.002614300625672357, "moe_gemm": 0.72402183586612, "moe_router": 0.017564069072735583, "norm_elementwise": 0.03839442593161487, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.19565666700967585, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0017527292718792177, "moe_gemm": 0.7535224022949394, "moe_router": 0.011441473126433909, "norm_elementwise": 0.02878152643291581, "sampler": 0.0 } }, "mode_steps": { "FULL": 7, "PIECEWISE": 1 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.7301095783988965 }, { "family": "attention", "rank": 2, "share": 0.20469223053211524 }, { "family": "norm_elementwise", "rank": 3, "share": 0.036410706151768 }, { "family": "moe_router", "rank": 4, "share": 0.016300609001782734 }, { "family": "kv_memory", "rank": 5, "share": 0.0024365065962538455 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -0.673985188837054, "mode_FULL": 0.11926397031787984, "mode_NONE": -0.2790993472934029, "mode_PIECEWISE": -0.0171348471830914, "prefill_fraction": -0.13753859346790945, "scheduled_tokens": -0.22985353117145157 }, "valid": false }, "shares": { "attention": 0.20469223053211524, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0024365065962538455, "moe_gemm": 0.7301095783988965, "moe_router": 0.016300609001782734, "norm_elementwise": 0.036410706151768, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 775.5859999999996, "name": "triton_poi_fused_3" }, { "duration_us": 562.3350000000004, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 541.5999999999998, "name": "triton_red_fused_2" }, { "duration_us": 22.592, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 16.384, "name": "triton_poi_fused_2" }, { "duration_us": 12.864999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 12.447999999999999, "name": "triton_red_fused_1" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.17098573558976576, "attention_mixed": 0.04244961271753521, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9900472542616138, "mode_shares": { "FULL": { "attention": 0.20867035579310442, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0025849579196340765, "moe_gemm": 0.7236684498934784, "moe_router": 0.017385853018663355, "norm_elementwise": 0.03743160202992195, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.23505546138588368, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0025209396629618792, "moe_gemm": 0.7060220856055816, "moe_router": 0.012259376230707445, "norm_elementwise": 0.035577961118325376, "sampler": 0.0 } }, "mode_steps": { "FULL": 7, "PIECEWISE": 1 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.7204816218764769 }, { "family": "attention", "rank": 2, "share": 0.21343534830730096 }, { "family": "norm_elementwise", "rank": 3, "share": 0.03709684555010769 }, { "family": "moe_router", "rank": 4, "share": 0.016460041922970896 }, { "family": "kv_memory", "rank": 5, "share": 0.0025733966047573075 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 14.182091081480554, "mode_FULL": 0.11926397031787984, "mode_NONE": -0.2790993472934029, "mode_PIECEWISE": -0.0171348471830914, "prefill_fraction": -0.20596870108215656, "scheduled_tokens": -0.2935716394203467 }, "valid": false }, "shares": { "attention": 0.21343534830730096, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0025733966047573075, "moe_gemm": 0.7204816218764769, "moe_router": 0.016460041922970896, "norm_elementwise": 0.03709684555010769, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 767.5569999999994, "name": "triton_poi_fused_3" }, { "duration_us": 572.6729999999994, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 527.8730000000002, "name": "triton_red_fused_2" }, { "duration_us": 22.624999999999996, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 16.192999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 12.735999999999999, "name": "triton_red_fused_1" }, { "duration_us": 11.902999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 2 } ], "P03-C00-moderate": [ { "attention_subshares": { "attention_decode": 0.23677440452100923, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9773142909813943, "mode_shares": { "FULL": { "attention": 0.23677440452100923, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.007300880477096696, "moe_gemm": 0.5916730425467414, "moe_router": 0.030667589074404745, "norm_elementwise": 0.11089837436214241, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5916730425467414 }, { "family": "attention", "rank": 2, "share": 0.23677440452100923 }, { "family": "norm_elementwise", "rank": 3, "share": 0.11089837436214241 }, { "family": "moe_router", "rank": 4, "share": 0.030667589074404745 }, { "family": "kv_memory", "rank": 5, "share": 0.007300880477096696 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 3.72009366381467, "mode_FULL": 0.27793577928319474, "mode_NONE": -0.27793577928319446, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.1868864933066391, "scheduled_tokens": -0.182101722961305 }, "valid": false }, "shares": { "attention": 0.23677440452100923, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.007300880477096696, "moe_gemm": 0.5916730425467414, "moe_router": 0.030667589074404745, "norm_elementwise": 0.11089837436214241, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 576.23, "name": "triton_poi_fused_3" }, { "duration_us": 464.7449999999998, "name": "triton_red_fused_2" }, { "duration_us": 19.744, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 12.575, "name": "triton_poi_fused_2" }, { "duration_us": 11.040999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 9.41, "name": "triton_red_fused_1" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.2295917342415148, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9711974069819732, "mode_shares": { "FULL": { "attention": 0.2295917342415148, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.009291871432449663, "moe_gemm": 0.5573510710995793, "moe_router": 0.04015146373050413, "norm_elementwise": 0.13481126647792535, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5573510710995793 }, { "family": "attention", "rank": 2, "share": 0.2295917342415148 }, { "family": "norm_elementwise", "rank": 3, "share": 0.13481126647792535 }, { "family": "moe_router", "rank": 4, "share": 0.04015146373050413 }, { "family": "kv_memory", "rank": 5, "share": 0.009291871432449663 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -0.27750213252727524, "mode_FULL": 0.27793577928319474, "mode_NONE": -0.27793577928319446, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.1868864933066391, "scheduled_tokens": -0.1838557206293655 }, "valid": false }, "shares": { "attention": 0.2295917342415148, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.009291871432449663, "moe_gemm": 0.5573510710995793, "moe_router": 0.04015146373050413, "norm_elementwise": 0.13481126647792535, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 571.9689999999993, "name": "triton_poi_fused_3" }, { "duration_us": 469.85699999999855, "name": "triton_red_fused_2" }, { "duration_us": 18.529, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 12.383, "name": "triton_poi_fused_2" }, { "duration_us": 9.761000000000001, "name": "triton_red_fused_1" } ], "valid": false, "window": 2 } ], "P04-C00-moderate": [ { "attention_subshares": { "attention_decode": 0.45337846230845036, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9811078968569179, "mode_shares": { "FULL": { "attention": 0.45337846230845036, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.00447249169315189, "moe_gemm": 0.4320822710822647, "moe_router": 0.03260980879841117, "norm_elementwise": 0.05856486297463963, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "attention", "rank": 1, "share": 0.45337846230845036 }, { "family": "moe_gemm", "rank": 2, "share": 0.4320822710822647 }, { "family": "norm_elementwise", "rank": 3, "share": 0.05856486297463963 }, { "family": "moe_router", "rank": 4, "share": 0.03260980879841117 }, { "family": "kv_memory", "rank": 5, "share": 0.00447249169315189 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 0.20844725339793926, "mode_FULL": 0.18226661968758462, "mode_NONE": -0.18226661968758412, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.15943564286260098, "scheduled_tokens": -0.15585724120282418 }, "valid": true }, "shares": { "attention": 0.45337846230845036, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.00447249169315189, "moe_gemm": 0.4320822710822647, "moe_router": 0.03260980879841117, "norm_elementwise": 0.05856486297463963, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 600.4589999999997, "name": "triton_poi_fused_3" }, { "duration_us": 503.8849999999992, "name": "triton_red_fused_2" }, { "duration_us": 467.6160000000004, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 19.391000000000002, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 12.958999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 11.197999999999999, "name": "triton_red_fused_1" }, { "duration_us": 9.726999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": true, "window": 1 }, { "attention_subshares": { "attention_decode": 0.5042949115154224, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.980970138873411, "mode_shares": { "FULL": { "attention": 0.5042949115154224, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004490478325551558, "moe_gemm": 0.3806685401425692, "moe_router": 0.032988086256013634, "norm_elementwise": 0.058528122633854276, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "attention", "rank": 1, "share": 0.5042949115154224 }, { "family": "moe_gemm", "rank": 2, "share": 0.3806685401425692 }, { "family": "norm_elementwise", "rank": 3, "share": 0.058528122633854276 }, { "family": "moe_router", "rank": 4, "share": 0.032988086256013634 }, { "family": "kv_memory", "rank": 5, "share": 0.004490478325551558 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 0.20844725339793926, "mode_FULL": 0.18226661968758462, "mode_NONE": -0.18226661968758412, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.15943564286260098, "scheduled_tokens": -0.15585724120282418 }, "valid": true }, "shares": { "attention": 0.5042949115154224, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004490478325551558, "moe_gemm": 0.3806685401425692, "moe_router": 0.032988086256013634, "norm_elementwise": 0.058528122633854276, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 600.0620000000005, "name": "triton_poi_fused_3" }, { "duration_us": 501.89399999999864, "name": "triton_red_fused_2" }, { "duration_us": 467.97200000000095, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 19.328, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 12.800999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 11.870999999999999, "name": "triton_red_fused_1" }, { "duration_us": 10.014999999999999, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": true, "window": 2 } ], "P06-C00-moderate": [ { "attention_subshares": { "attention_decode": 0.2490290455613554, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9782676099166654, "mode_shares": { "FULL": { "attention": 0.2490290455613554, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.005145523506508112, "moe_gemm": 0.6200403635488907, "moe_router": 0.03550127037050399, "norm_elementwise": 0.06855140692940716, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.6200403635488907 }, { "family": "attention", "rank": 2, "share": 0.2490290455613554 }, { "family": "norm_elementwise", "rank": 3, "share": 0.06855140692940716 }, { "family": "moe_router", "rank": 4, "share": 0.03550127037050399 }, { "family": "kv_memory", "rank": 5, "share": 0.005145523506508112 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -0.7216535064826213, "mode_FULL": 0.13539969781837916, "mode_NONE": -0.1341287527105229, "mode_PIECEWISE": -0.018343220956176326, "prefill_fraction": -0.13284443594178524, "scheduled_tokens": -0.12475886497271786 }, "valid": false }, "shares": { "attention": 0.2490290455613554, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.005145523506508112, "moe_gemm": 0.6200403635488907, "moe_router": 0.03550127037050399, "norm_elementwise": 0.06855140692940716, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 597.553, "name": "triton_poi_fused_3" }, { "duration_us": 503.07699999999915, "name": "triton_red_fused_2" }, { "duration_us": 466.9400000000012, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 19.869999999999997, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.854, "name": "triton_poi_fused_2" }, { "duration_us": 11.744, "name": "triton_red_fused_1" }, { "duration_us": 9.727, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.382897364177646, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9857570160520932, "mode_shares": { "FULL": { "attention": 0.382897364177646, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003409296822253497, "moe_gemm": 0.5303535709645394, "moe_router": 0.023879803771651553, "norm_elementwise": 0.04521698031600275, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5303535709645394 }, { "family": "attention", "rank": 2, "share": 0.382897364177646 }, { "family": "norm_elementwise", "rank": 3, "share": 0.04521698031600275 }, { "family": "moe_router", "rank": 4, "share": 0.023879803771651553 }, { "family": "kv_memory", "rank": 5, "share": 0.003409296822253497 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 2.7828468550637027, "mode_FULL": 0.13539969781837916, "mode_NONE": -0.1341287527105229, "mode_PIECEWISE": -0.018343220956176326, "prefill_fraction": -0.13284443594178524, "scheduled_tokens": -0.10682572566427663 }, "valid": false }, "shares": { "attention": 0.382897364177646, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003409296822253497, "moe_gemm": 0.5303535709645394, "moe_router": 0.023879803771651553, "norm_elementwise": 0.04521698031600275, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 620.7480000000002, "name": "triton_poi_fused_3" }, { "duration_us": 515.2009999999995, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 493.54399999999913, "name": "triton_red_fused_2" }, { "duration_us": 19.936, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.312, "name": "triton_poi_fused_2" }, { "duration_us": 10.751999999999999, "name": "triton_red_fused_1" }, { "duration_us": 10.4, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 2 } ], "P07-C00-moderate": [ { "attention_subshares": { "attention_decode": 0.306761436001029, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9841089106220091, "mode_shares": { "FULL": { "attention": 0.306761436001029, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003944802403864725, "moe_gemm": 0.5964090291561805, "moe_router": 0.02562456323133302, "norm_elementwise": 0.051369079829601885, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5964090291561805 }, { "family": "attention", "rank": 2, "share": 0.306761436001029 }, { "family": "norm_elementwise", "rank": 3, "share": 0.051369079829601885 }, { "family": "moe_router", "rank": 4, "share": 0.02562456323133302 }, { "family": "kv_memory", "rank": 5, "share": 0.003944802403864725 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -0.18368608035893982, "mode_FULL": 0.1535286967084372, "mode_NONE": -0.15352869670843752, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.1535266720575854, "scheduled_tokens": -0.13391206652423035 }, "valid": true }, "shares": { "attention": 0.306761436001029, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003944802403864725, "moe_gemm": 0.5964090291561805, "moe_router": 0.02562456323133302, "norm_elementwise": 0.051369079829601885, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 606.694, "name": "triton_poi_fused_3" }, { "duration_us": 538.9419999999992, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 496.9549999999989, "name": "triton_red_fused_2" }, { "duration_us": 20.128, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 15.04, "name": "triton_poi_fused_2" }, { "duration_us": 10.56, "name": "triton_red_fused_1" }, { "duration_us": 10.304, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.2666065580814879, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9860189886811974, "mode_shares": { "FULL": { "attention": 0.2666065580814879, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0034992714146667428, "moe_gemm": 0.6472552645315595, "moe_router": 0.02277286906470575, "norm_elementwise": 0.04588502558877749, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.6472552645315595 }, { "family": "attention", "rank": 2, "share": 0.2666065580814879 }, { "family": "norm_elementwise", "rank": 3, "share": 0.04588502558877749 }, { "family": "moe_router", "rank": 4, "share": 0.02277286906470575 }, { "family": "kv_memory", "rank": 5, "share": 0.0034992714146667428 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 3.069910871828644, "mode_FULL": 0.1535286967084372, "mode_NONE": -0.15352869670843752, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.1535266720575854, "scheduled_tokens": -0.11608746652035899 }, "valid": false }, "shares": { "attention": 0.2666065580814879, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0034992714146667428, "moe_gemm": 0.6472552645315595, "moe_router": 0.02277286906470575, "norm_elementwise": 0.04588502558877749, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 621.5659999999995, "name": "triton_poi_fused_3" }, { "duration_us": 529.2479999999987, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 510.27699999999976, "name": "triton_red_fused_2" }, { "duration_us": 20.607000000000003, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.184, "name": "triton_poi_fused_2" }, { "duration_us": 11.230999999999998, "name": "triton_red_fused_1" }, { "duration_us": 10.817, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 2 } ], "P08-C00-moderate": [ { "attention_subshares": { "attention_decode": 0.3248872069635257, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9877052895017178, "mode_shares": { "FULL": { "attention": 0.3248872069635257, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0031072028443770152, "moe_gemm": 0.5984635601986847, "moe_router": 0.020260919566213807, "norm_elementwise": 0.04098639992891659, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5984635601986847 }, { "family": "attention", "rank": 2, "share": 0.3248872069635257 }, { "family": "norm_elementwise", "rank": 3, "share": 0.04098639992891659 }, { "family": "moe_router", "rank": 4, "share": 0.020260919566213807 }, { "family": "kv_memory", "rank": 5, "share": 0.0031072028443770152 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 1.0901560791930118, "mode_FULL": 0.16434181266464418, "mode_NONE": -0.16434181266464443, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.16432997461824633, "scheduled_tokens": -0.1413297101061453 }, "valid": false }, "shares": { "attention": 0.3248872069635257, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0031072028443770152, "moe_gemm": 0.5984635601986847, "moe_router": 0.020260919566213807, "norm_elementwise": 0.04098639992891659, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 654.3379999999997, "name": "triton_poi_fused_3" }, { "duration_us": 552.4199999999996, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 513.1979999999996, "name": "triton_red_fused_2" }, { "duration_us": 21.089000000000002, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 14.015999999999998, "name": "triton_poi_fused_2" }, { "duration_us": 12.127999999999998, "name": "triton_red_fused_1" }, { "duration_us": 10.719, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.3669917099645223, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9854450802968766, "mode_shares": { "FULL": { "attention": 0.3669917099645223, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003724234761488658, "moe_gemm": 0.5428235608185195, "moe_router": 0.024088695306046685, "norm_elementwise": 0.04781687944629951, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5428235608185195 }, { "family": "attention", "rank": 2, "share": 0.3669917099645223 }, { "family": "norm_elementwise", "rank": 3, "share": 0.04781687944629951 }, { "family": "moe_router", "rank": 4, "share": 0.024088695306046685 }, { "family": "kv_memory", "rank": 5, "share": 0.003724234761488658 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -1.4164397504981734, "mode_FULL": 0.16434181266464418, "mode_NONE": -0.16434181266464443, "mode_PIECEWISE": 0.0, "prefill_fraction": -0.16432997461824633, "scheduled_tokens": -0.19075947310069616 }, "valid": false }, "shares": { "attention": 0.3669917099645223, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.003724234761488658, "moe_gemm": 0.5428235608185195, "moe_router": 0.024088695306046685, "norm_elementwise": 0.04781687944629951, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 632.7909999999997, "name": "triton_poi_fused_3" }, { "duration_us": 540.1919999999998, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 511.9399999999992, "name": "triton_red_fused_2" }, { "duration_us": 20.673000000000002, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.665, "name": "triton_poi_fused_2" }, { "duration_us": 11.713, "name": "triton_red_fused_1" }, { "duration_us": 10.878999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 2 } ], "P09-C00-moderate": [ { "attention_subshares": { "attention_decode": 0.08835627115447606, "attention_mixed": 0.11385037570991731, "attention_prefill": 0.0 }, "classifiable_fraction": 0.988346330660954, "mode_shares": { "FULL": { "attention": 0.280249688903593, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004209638462393143, "moe_gemm": 0.6254634471394533, "moe_router": 0.02523969717175661, "norm_elementwise": 0.0493304218340256, "sampler": 0.0 }, "NONE": { "attention": 0.14806901527656063, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0, "moe_gemm": 0.7989631873012853, "moe_router": 0.006717474937844798, "norm_elementwise": 0.036240204978569675, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.18871401371634564, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0022585830433693877, "moe_gemm": 0.7546316751137306, "moe_router": 0.012749732426996046, "norm_elementwise": 0.031927806640493814, "sampler": 0.0 } }, "mode_steps": { "FULL": 5, "NONE": 1, "PIECEWISE": 2 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.7306681072672004 }, { "family": "attention", "rank": 2, "share": 0.20220664686439338 }, { "family": "norm_elementwise", "rank": 3, "share": 0.039044817770315786 }, { "family": "moe_router", "rank": 4, "share": 0.014406944379520907 }, { "family": "kv_memory", "rank": 5, "share": 0.002019814379523439 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 2.5579606107986748, "mode_FULL": -0.6775421426296558, "mode_NONE": 0.2503307644752007, "mode_PIECEWISE": 0.5907929693818461, "prefill_fraction": 0.6661033678566376, "scheduled_tokens": 0.05206272885676596 }, "valid": false }, "shares": { "attention": 0.20220664686439338, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.002019814379523439, "moe_gemm": 0.7306681072672004, "moe_router": 0.014406944379520907, "norm_elementwise": 0.039044817770315786, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 1078.7899999999981, "name": "triton_poi_fused_3" }, { "duration_us": 718.971000000001, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 663.9299999999997, "name": "triton_red_fused_2" }, { "duration_us": 22.880000000000003, "name": "triton_poi_fused_2" }, { "duration_us": 22.017, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 14.112, "name": "triton_red_fused_1" }, { "duration_us": 10.974999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.09568605186600879, "attention_mixed": 0.025924532025613695, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9819166279177437, "mode_shares": { "FULL": { "attention": 0.14040386061386476, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.006289384167983417, "moe_gemm": 0.7278572814656825, "moe_router": 0.03517706269456804, "norm_elementwise": 0.06867748249282202, "sampler": 0.0 }, "PIECEWISE": { "attention": 0.08139719907850929, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.0022138539380632135, "moe_gemm": 0.8578037652991323, "moe_router": 0.01403539873195149, "norm_elementwise": 0.033980351851418185, "sampler": 0.0 } }, "mode_steps": { "FULL": 7, "PIECEWISE": 1 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.7692444768470234 }, { "family": "attention", "rank": 2, "share": 0.12161058389162249 }, { "family": "norm_elementwise", "rank": 3, "share": 0.05762664923697027 }, { "family": "moe_router", "rank": 4, "share": 0.028443566325178558 }, { "family": "kv_memory", "rank": 5, "share": 0.004991351616949132 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -0.19954189900373331, "mode_FULL": -0.10469513477046205, "mode_NONE": -0.32861907697425397, "mode_PIECEWISE": 0.29736821980293143, "prefill_fraction": 0.10420387771831544, "scheduled_tokens": -0.23288793337699637 }, "valid": false }, "shares": { "attention": 0.12161058389162249, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.004991351616949132, "moe_gemm": 0.7692444768470234, "moe_router": 0.028443566325178558, "norm_elementwise": 0.05762664923697027, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 667.7419999999993, "name": "triton_poi_fused_3" }, { "duration_us": 523.011999999999, "name": "triton_red_fused_2" }, { "duration_us": 498.98300000000086, "name": "void vllm::moe::count_and_sort_expert_tokens_kernel(int const*, int*, int*, int*, unsigned long, int, int, int, bool)" }, { "duration_us": 20.736, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 14.591, "name": "triton_poi_fused_2" }, { "duration_us": 11.645, "name": "triton_red_fused_1" }, { "duration_us": 11.36, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" } ], "valid": false, "window": 2 } ], "P10-C00-moderate": [ { "attention_subshares": { "attention_decode": 0.3087850643091725, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.985252225101006, "mode_shares": { "FULL": { "attention": 0.3087850643091725, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.005163136163815447, "moe_gemm": 0.5777999387887653, "moe_router": 0.02008575072504131, "norm_elementwise": 0.07341833511421153, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5777999387887653 }, { "family": "attention", "rank": 2, "share": 0.3087850643091725 }, { "family": "norm_elementwise", "rank": 3, "share": 0.07341833511421153 }, { "family": "moe_router", "rank": 4, "share": 0.02008575072504131 }, { "family": "kv_memory", "rank": 5, "share": 0.005163136163815447 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": 4.655696267017126, "mode_FULL": 0.17677689026422408, "mode_NONE": -0.1682723158645361, "mode_PIECEWISE": -0.05341411394958018, "prefill_fraction": -0.12905587442539998, "scheduled_tokens": -0.09951290348812954 }, "valid": false }, "shares": { "attention": 0.3087850643091725, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.005163136163815447, "moe_gemm": 0.5777999387887653, "moe_router": 0.02008575072504131, "norm_elementwise": 0.07341833511421153, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 583.5649999999997, "name": "triton_poi_fused_3" }, { "duration_us": 466.8209999999995, "name": "triton_red_fused_2" }, { "duration_us": 19.617, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.536, "name": "triton_poi_fused_2" }, { "duration_us": 11.231999999999998, "name": "void at::native::vectorized_gather_kernel<16, long>(char*, char*, long*, int, long, long, long, long, bool)" }, { "duration_us": 10.049, "name": "triton_red_fused_1" } ], "valid": false, "window": 1 }, { "attention_subshares": { "attention_decode": 0.3033378915990537, "attention_mixed": 0.0, "attention_prefill": 0.0 }, "classifiable_fraction": 0.9736215707793747, "mode_shares": { "FULL": { "attention": 0.3033378915990537, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.008423712471036498, "moe_gemm": 0.5030357454817748, "moe_router": 0.03618969859772223, "norm_elementwise": 0.12263452262978754, "sampler": 0.0 } }, "mode_steps": { "FULL": 8 }, "ranking": [ { "family": "moe_gemm", "rank": 1, "share": 0.5030357454817748 }, { "family": "attention", "rank": 2, "share": 0.3033378915990537 }, { "family": "norm_elementwise", "rank": 3, "share": 0.12263452262978754 }, { "family": "moe_router", "rank": 4, "share": 0.03618969859772223 }, { "family": "kv_memory", "rank": 5, "share": 0.008423712471036498 }, { "family": "collective", "rank": 5, "share": 0.0 }, { "family": "sampler", "rank": 5, "share": 0.0 }, { "family": "dense_gemm", "rank": 5, "share": 0.0 } ], "representativeness": { "smd": { "decode_batch_size": -0.5055344205281964, "mode_FULL": 0.17677689026422408, "mode_NONE": -0.1682723158645361, "mode_PIECEWISE": -0.05341411394958018, "prefill_fraction": -0.12905587442539998, "scheduled_tokens": -0.10506250419671144 }, "valid": false }, "shares": { "attention": 0.3033378915990537, "collective": 0.0, "dense_gemm": 0.0, "kv_memory": 0.008423712471036498, "moe_gemm": 0.5030357454817748, "moe_router": 0.03618969859772223, "norm_elementwise": 0.12263452262978754, "sampler": 0.0 }, "top_unmatched": [ { "duration_us": 590.9459999999992, "name": "triton_poi_fused_3" }, { "duration_us": 467.6929999999989, "name": "triton_red_fused_2" }, { "duration_us": 18.272, "name": "_compute_slot_mapping_kernel" }, { "duration_us": 13.152, "name": "triton_poi_fused_2" }, { "duration_us": 9.63, "name": "triton_red_fused_1" } ], "valid": false, "window": 2 } ] }, "ranking": { "accepted_inversions": [], "candidates": [], "completed_patterns": [ "P01", "P02", "P03", "P04", "P06", "P07", "P08", "P09", "P10" ], "evaluable_patterns": [ "P04" ], "invalid_primary_windows": [ "P01-C00-moderate: window 1", "P01-C00-moderate: window 2", "P02-C00-moderate: window 1", "P02-C00-moderate: window 2", "P03-C00-moderate: window 1", "P03-C00-moderate: window 2", "P06-C00-moderate: window 1", "P06-C00-moderate: window 2", "P07-C00-moderate: window 1", "P07-C00-moderate: window 2", "P08-C00-moderate: window 1", "P08-C00-moderate: window 2", "P09-C00-moderate: window 1", "P09-C00-moderate: window 2", "P10-C00-moderate: window 1", "P10-C00-moderate: window 2" ], "kendall_tau_b": [], "missing_patterns": [ "P05", "P11" ], "tests": 1540 }, "robustness": { "confirmation_runs": "NOT_EVALUABLE: all four confirmations are missing", "mixed_interference": "leave-one-pattern-out fits applied within config/load", "operator_ranking": "two fixed wall-separated windows; no separate LOAO procedure was preregistered" }, "runs": { "P01-C00-moderate": { "blocks": [ { "bucket": 30576.0, "duration_ms": 9977.070185999999, "eligible_miss": 0.0, "miss": 33.0, "model": 116.0, "overflow": 33.0, "padding": 603.0, "tokens": 50505.0 }, { "bucket": 29728.0, "duration_ms": 10025.674661000003, "eligible_miss": 0.0, "miss": 33.0, "model": 119.0, "overflow": 33.0, "padding": 537.0, "tokens": 49844.0 }, { "bucket": 31568.0, "duration_ms": 9953.621208999997, "eligible_miss": 0.0, "miss": 29.0, "model": 120.0, "overflow": 29.0, "padding": 545.0, "tokens": 49319.0 }, { "bucket": 26832.0, "duration_ms": 9914.660198999998, "eligible_miss": 0.0, "miss": 38.0, "model": 116.0, "overflow": 38.0, "padding": 503.0, "tokens": 49709.0 }, { "bucket": 31992.0, "duration_ms": 10027.674603000003, "eligible_miss": 0.0, "miss": 27.0, "model": 126.0, "overflow": 27.0, "padding": 574.0, "tokens": 47825.0 }, { "bucket": 33224.0, "duration_ms": 9940.844814, "eligible_miss": 0.0, "miss": 29.0, "model": 120.0, "overflow": 29.0, "padding": 627.0, "tokens": 49561.0 }, { "bucket": 33456.0, "duration_ms": 10001.052717999995, "eligible_miss": 0.0, "miss": 26.0, "model": 128.0, "overflow": 26.0, "padding": 565.0, "tokens": 48243.0 }, { "bucket": 34136.0, "duration_ms": 9976.993478999995, "eligible_miss": 0.0, "miss": 24.0, "model": 123.0, "overflow": 24.0, "padding": 618.0, "tokens": 49143.0 }, { "bucket": 31224.0, "duration_ms": 9995.576178, "eligible_miss": 0.0, "miss": 32.0, "model": 118.0, "overflow": 32.0, "padding": 610.0, "tokens": 50258.0 }, { "bucket": 31800.0, "duration_ms": 9989.647112, "eligible_miss": 0.0, "miss": 29.0, "model": 121.0, "overflow": 29.0, "padding": 583.0, "tokens": 49181.0 }, { "bucket": 36560.0, "duration_ms": 9966.385023999997, "eligible_miss": 0.0, "miss": 21.0, "model": 125.0, "overflow": 21.0, "padding": 660.0, "tokens": 48591.0 }, { "bucket": 25560.0, "duration_ms": 10003.187468000002, "eligible_miss": 0.0, "miss": 43.0, "model": 117.0, "overflow": 43.0, "padding": 490.0, "tokens": 51245.0 }, { "bucket": 27448.0, "duration_ms": 9971.533022999996, "eligible_miss": 0.0, "miss": 39.0, "model": 113.0, "overflow": 39.0, "padding": 525.0, "tokens": 51806.0 }, { "bucket": 29384.0, "duration_ms": 9983.114686000003, "eligible_miss": 0.0, "miss": 35.0, "model": 115.0, "overflow": 35.0, "padding": 564.0, "tokens": 50967.0 }, { "bucket": 29688.0, "duration_ms": 9990.978558, "eligible_miss": 0.0, "miss": 34.0, "model": 121.0, "overflow": 34.0, "padding": 571.0, "tokens": 49442.0 }, { "bucket": 33376.0, "duration_ms": 9995.658681999994, "eligible_miss": 0.0, "miss": 27.0, "model": 121.0, "overflow": 27.0, "padding": 615.0, "tokens": 49129.0 }, { "bucket": 31432.0, "duration_ms": 10015.605592999998, "eligible_miss": 0.0, "miss": 31.0, "model": 118.0, "overflow": 31.0, "padding": 599.0, "tokens": 50125.0 }, { "bucket": 29048.0, "duration_ms": 9974.7466, "eligible_miss": 0.0, "miss": 35.0, "model": 116.0, "overflow": 35.0, "padding": 529.0, "tokens": 50381.0 }, { "bucket": 31256.0, "duration_ms": 9993.147903, "eligible_miss": 0.0, "miss": 32.0, "model": 121.0, "overflow": 32.0, "padding": 660.0, "tokens": 49683.0 }, { "bucket": 33984.0, "duration_ms": 9963.886105999996, "eligible_miss": 0.0, "miss": 26.0, "model": 121.0, "overflow": 26.0, "padding": 658.0, "tokens": 49368.0 }, { "bucket": 31320.0, "duration_ms": 10029.250221999997, "eligible_miss": 0.0, "miss": 32.0, "model": 118.0, "overflow": 32.0, "padding": 528.0, "tokens": 50904.0 }, { "bucket": 31120.0, "duration_ms": 10007.011493000004, "eligible_miss": 0.0, "miss": 33.0, "model": 114.0, "overflow": 33.0, "padding": 499.0, "tokens": 51082.0 }, { "bucket": 33296.0, "duration_ms": 9953.774958000002, "eligible_miss": 0.0, "miss": 26.0, "model": 121.0, "overflow": 26.0, "padding": 607.0, "tokens": 48871.0 }, { "bucket": 30576.0, "duration_ms": 9998.836994000001, "eligible_miss": 0.0, "miss": 32.0, "model": 120.0, "overflow": 32.0, "padding": 633.0, "tokens": 50044.0 }, { "bucket": 35040.0, "duration_ms": 9907.035887999995, "eligible_miss": 0.0, "miss": 22.0, "model": 121.0, "overflow": 22.0, "padding": 614.0, "tokens": 48318.0 }, { "bucket": 31816.0, "duration_ms": 9997.940913000004, "eligible_miss": 0.0, "miss": 30.0, "model": 114.0, "overflow": 30.0, "padding": 557.0, "tokens": 51711.0 }, { "bucket": 31464.0, "duration_ms": 10054.742900999996, "eligible_miss": 0.0, "miss": 30.0, "model": 122.0, "overflow": 30.0, "padding": 605.0, "tokens": 48442.0 }, { "bucket": 31064.0, "duration_ms": 9932.345599, "eligible_miss": 0.0, "miss": 32.0, "model": 120.0, "overflow": 32.0, "padding": 589.0, "tokens": 49398.0 }, { "bucket": 32760.0, "duration_ms": 10010.170066999997, "eligible_miss": 0.0, "miss": 27.0, "model": 128.0, "overflow": 27.0, "padding": 660.0, "tokens": 47928.0 }, { "bucket": 33432.0, "duration_ms": 9968.922715000002, "eligible_miss": 0.0, "miss": 26.0, "model": 118.0, "overflow": 26.0, "padding": 671.0, "tokens": 49679.0 }, { "bucket": 29392.0, "duration_ms": 10013.087841999995, "eligible_miss": 0.0, "miss": 34.0, "model": 118.0, "overflow": 34.0, "padding": 541.0, "tokens": 49880.0 }, { "bucket": 28832.0, "duration_ms": 9938.452419999998, "eligible_miss": 0.0, "miss": 35.0, "model": 115.0, "overflow": 35.0, "padding": 559.0, "tokens": 51143.0 }, { "bucket": 33672.0, "duration_ms": 10049.196139999996, "eligible_miss": 0.0, "miss": 27.0, "model": 124.0, "overflow": 27.0, "padding": 689.0, "tokens": 48878.0 }, { "bucket": 35856.0, "duration_ms": 9952.635497000005, "eligible_miss": 0.0, "miss": 21.0, "model": 123.0, "overflow": 21.0, "padding": 647.0, "tokens": 48258.0 }, { "bucket": 27608.0, "duration_ms": 9958.917514999996, "eligible_miss": 0.0, "miss": 39.0, "model": 112.0, "overflow": 39.0, "padding": 503.0, "tokens": 51781.0 }, { "bucket": 35256.0, "duration_ms": 10019.95564, "eligible_miss": 0.0, "miss": 22.0, "model": 126.0, "overflow": 22.0, "padding": 667.0, "tokens": 47965.0 }, { "bucket": 36024.0, "duration_ms": 9971.399555000004, "eligible_miss": 0.0, "miss": 21.0, "model": 124.0, "overflow": 21.0, "padding": 743.0, "tokens": 47961.0 }, { "bucket": 35056.0, "duration_ms": 9981.311274000002, "eligible_miss": 0.0, "miss": 22.0, "model": 127.0, "overflow": 22.0, "padding": 664.0, "tokens": 47846.0 }, { "bucket": 27520.0, "duration_ms": 10008.593500999998, "eligible_miss": 0.0, "miss": 39.0, "model": 115.0, "overflow": 39.0, "padding": 460.0, "tokens": 52024.0 }, { "bucket": 32248.0, "duration_ms": 9955.697573, "eligible_miss": 0.0, "miss": 28.0, "model": 122.0, "overflow": 28.0, "padding": 566.0, "tokens": 48422.0 }, { "bucket": 31312.0, "duration_ms": 9951.151515, "eligible_miss": 0.0, "miss": 31.0, "model": 122.0, "overflow": 31.0, "padding": 524.0, "tokens": 48815.0 }, { "bucket": 36640.0, "duration_ms": 10005.843674999998, "eligible_miss": 0.0, "miss": 19.0, "model": 126.0, "overflow": 19.0, "padding": 675.0, "tokens": 47758.0 }, { "bucket": 36104.0, "duration_ms": 9967.80646, "eligible_miss": 0.0, "miss": 21.0, "model": 128.0, "overflow": 21.0, "padding": 695.0, "tokens": 47577.0 }, { "bucket": 31296.0, "duration_ms": 10039.968077000001, "eligible_miss": 0.0, "miss": 31.0, "model": 120.0, "overflow": 31.0, "padding": 603.0, "tokens": 50038.0 }, { "bucket": 28720.0, "duration_ms": 9947.777837999993, "eligible_miss": 0.0, "miss": 37.0, "model": 115.0, "overflow": 37.0, "padding": 521.0, "tokens": 50984.0 }, { "bucket": 30752.0, "duration_ms": 9989.05891, "eligible_miss": 0.0, "miss": 32.0, "model": 115.0, "overflow": 32.0, "padding": 582.0, "tokens": 50810.0 }, { "bucket": 31528.0, "duration_ms": 10007.517981999998, "eligible_miss": 0.0, "miss": 30.0, "model": 117.0, "overflow": 30.0, "padding": 631.0, "tokens": 50638.0 }, { "bucket": 33064.0, "duration_ms": 10068.188278999998, "eligible_miss": 0.0, "miss": 28.0, "model": 120.0, "overflow": 28.0, "padding": 637.0, "tokens": 49561.0 } ], "clean": { "admitted": 6235, "completed": 6232, "completed_throughput_rps": 25.966666666666665, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 1986493, "offered_rps": 25.979166666666668, "output_tokens": 398848, "start_s": 60.0 }, "config": "C00", "drain_quarantined": false, "drain_seconds": 1.0203027040115558, "latency_s": { "e2e": { "mean": 2.7387289799440433, "n": 6232, "p50": 2.737939690996427, "p95": 2.9280695282504894, "p99": 2.993426457623136 }, "tpot": { "mean": 0.04167998409546577, "n": 6232, "p50": 0.04166355157120427, "p95": 0.04453765388101428, "p99": 0.045556931762553245 }, "ttft": { "mean": 0.11288998192969947, "n": 6232, "p50": 0.11091382149606943, "p95": 0.1447070966445608, "p99": 0.1583496381092118 } }, "layer1": { "decode_tokens": 392669, "kv_usage_max": 0.10235198702351989, "kv_usage_mean": 0.08515698687332914, "mode_counts": { "FULL": 114, "NONE": 1430, "PIECEWISE": 4216 }, "mode_shares": { "FULL": 0.019791666666666666, "NONE": 0.2482638888888889, "PIECEWISE": 0.7319444444444444 }, "preemptions": 0, "prefill_tokens": 1988372, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 0, "queue_waiting_mean": 0.0, "records_all": 8361, "records_clean": 5760, "requests_per_step": { "mean": 69.25416666666666, "n": 5760, "p50": 69.0, "p95": 74.0, "p99": 76.0 }, "scheduled_tokens_per_step": { "mean": 413.3751736111111, "n": 5760, "p50": 402.0, "p95": 711.0, "p99": 922.0 }, "step_duration_ms": { "mean": 83.22007816753472, "n": 5760, "p50": 83.618554, "p95": 100.98220115, "p99": 111.06512396999999 }, "token_efficiency_per_ms": 4.967252887925961 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P01", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 26.15, "clean_c_waiting_median": 0.0, "completion_rate_rps": 26.2, "completion_rate_within_10pct": true, "tail_end_s": 340.92300570901716, "tail_start_s": 330.92300570901716, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 26.15, "clean_c_waiting_median": 0.0, "completion_rate_rps": 26.3, "completion_rate_within_10pct": true, "tail_end_s": 381.4778159119887, "tail_start_s": 371.4778159119887, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": true, "requests_completed": 6232, "run_dir": "runs/phase3/primary/P01-C00/moderate", "run_id": "P01-C00-moderate", "trace_files": 2, "waste": { "R128": 0.3723323346172142, "R32": 0.3612776759520059, "R64": 0.36868249852408347, "bucket_slack": 0.018691968735246287, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.2482638888888889, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 5646, "moe_layer_cv": null, "overflow_rate": 0.2482638888888889, "padded_tokens_per_useful_token": 0.011972074399390855, "padding_fraction": 0.018691968735246287 } }, "P01-C00-saturation": { "blocks": [ { "bucket": 13312.0, "duration_ms": 9700.4556, "eligible_miss": 0.0, "miss": 8.0, "model": 60.0, "overflow": 8.0, "padding": 1.0, "tokens": 73007.0 }, { "bucket": 7536.0, "duration_ms": 9932.258910999999, "eligible_miss": 0.0, "miss": 12.0, "model": 41.0, "overflow": 12.0, "padding": 19.0, "tokens": 90414.0 }, { "bucket": 6888.0, "duration_ms": 10178.935983, "eligible_miss": 0.0, "miss": 13.0, "model": 40.0, "overflow": 13.0, "padding": 5.0, "tokens": 94514.0 }, { "bucket": 13960.0, "duration_ms": 10457.795198000002, "eligible_miss": 0.0, "miss": 10.0, "model": 64.0, "overflow": 10.0, "padding": 7.0, "tokens": 85573.0 }, { "bucket": 14040.0, "duration_ms": 10337.022535999999, "eligible_miss": 0.0, "miss": 10.0, "model": 64.0, "overflow": 10.0, "padding": 6.0, "tokens": 81261.0 }, { "bucket": 13544.0, "duration_ms": 9714.938590000002, "eligible_miss": 0.0, "miss": 10.0, "model": 63.0, "overflow": 10.0, "padding": 5.0, "tokens": 75029.0 }, { "bucket": 13544.0, "duration_ms": 9903.635449, "eligible_miss": 0.0, "miss": 10.0, "model": 63.0, "overflow": 10.0, "padding": 5.0, "tokens": 75289.0 }, { "bucket": 7168.0, "duration_ms": 9403.655798000002, "eligible_miss": 0.0, "miss": 10.0, "model": 38.0, "overflow": 10.0, "padding": 0.0, "tokens": 85622.0 }, { "bucket": 7800.0, "duration_ms": 9955.373708000003, "eligible_miss": 0.0, "miss": 12.0, "model": 42.0, "overflow": 12.0, "padding": 19.0, "tokens": 88933.0 }, { "bucket": 12728.0, "duration_ms": 10579.801631999999, "eligible_miss": 0.0, "miss": 11.0, "model": 61.0, "overflow": 11.0, "padding": 6.0, "tokens": 90349.0 }, { "bucket": 13768.0, "duration_ms": 9765.536687999997, "eligible_miss": 0.0, "miss": 9.0, "model": 63.0, "overflow": 9.0, "padding": 16.0, "tokens": 76354.0 }, { "bucket": 14200.0, "duration_ms": 10142.375634000004, "eligible_miss": 0.0, "miss": 9.0, "model": 64.0, "overflow": 9.0, "padding": 23.0, "tokens": 80248.0 }, { "bucket": 13768.0, "duration_ms": 10205.201202, "eligible_miss": 0.0, "miss": 10.0, "model": 64.0, "overflow": 10.0, "padding": 13.0, "tokens": 80905.0 }, { "bucket": 11008.0, "duration_ms": 9274.425237, "eligible_miss": 0.0, "miss": 8.0, "model": 51.0, "overflow": 8.0, "padding": 0.0, "tokens": 74036.0 }, { "bucket": 7624.0, "duration_ms": 9966.902078, "eligible_miss": 0.0, "miss": 12.0, "model": 42.0, "overflow": 12.0, "padding": 13.0, "tokens": 90176.0 }, { "bucket": 8904.0, "duration_ms": 10401.74154, "eligible_miss": 0.0, "miss": 12.0, "model": 47.0, "overflow": 12.0, "padding": 11.0, "tokens": 95189.0 }, { "bucket": 13768.0, "duration_ms": 9996.728811, "eligible_miss": 0.0, "miss": 10.0, "model": 64.0, "overflow": 10.0, "padding": 11.0, "tokens": 78683.0 }, { "bucket": 13768.0, "duration_ms": 10098.225219, "eligible_miss": 0.0, "miss": 10.0, "model": 64.0, "overflow": 10.0, "padding": 11.0, "tokens": 81135.0 }, { "bucket": 13768.0, "duration_ms": 10336.009350000002, "eligible_miss": 0.0, "miss": 10.0, "model": 64.0, "overflow": 10.0, "padding": 11.0, "tokens": 82320.0 }, { "bucket": 14232.0, "duration_ms": 9508.483533000002, "eligible_miss": 0.0, "miss": 8.0, "model": 63.0, "overflow": 8.0, "padding": 25.0, "tokens": 74058.0 }, { "bucket": 11520.0, "duration_ms": 9614.615344999998, "eligible_miss": 0.0, "miss": 9.0, "model": 54.0, "overflow": 9.0, "padding": 0.0, "tokens": 77327.0 }, { "bucket": 6344.0, "duration_ms": 10036.276204, "eligible_miss": 0.0, "miss": 13.0, "model": 38.0, "overflow": 13.0, "padding": 11.0, "tokens": 93120.0 }, { "bucket": 9416.0, "duration_ms": 10347.189429000002, "eligible_miss": 0.0, "miss": 12.0, "model": 49.0, "overflow": 12.0, "padding": 11.0, "tokens": 93721.0 }, { "bucket": 13512.0, "duration_ms": 10252.652897, "eligible_miss": 0.0, "miss": 11.0, "model": 64.0, "overflow": 11.0, "padding": 11.0, "tokens": 81378.0 }, { "bucket": 13976.0, "duration_ms": 10021.668533, "eligible_miss": 0.0, "miss": 10.0, "model": 64.0, "overflow": 10.0, "padding": 22.0, "tokens": 79064.0 }, { "bucket": 13928.0, "duration_ms": 10279.847324999997, "eligible_miss": 0.0, "miss": 10.0, "model": 64.0, "overflow": 10.0, "padding": 20.0, "tokens": 82321.0 }, { "bucket": 13512.0, "duration_ms": 9703.471726999998, "eligible_miss": 0.0, "miss": 10.0, "model": 63.0, "overflow": 10.0, "padding": 11.0, "tokens": 75946.0 }, { "bucket": 8448.0, "duration_ms": 9304.457085999997, "eligible_miss": 0.0, "miss": 10.0, "model": 43.0, "overflow": 10.0, "padding": 0.0, "tokens": 78700.0 }, { "bucket": 7112.0, "duration_ms": 10029.146659999999, "eligible_miss": 0.0, "miss": 13.0, "model": 41.0, "overflow": 13.0, "padding": 11.0, "tokens": 90998.0 }, { "bucket": 11656.0, "duration_ms": 10649.044713000001, "eligible_miss": 0.0, "miss": 11.0, "model": 57.0, "overflow": 11.0, "padding": 11.0, "tokens": 93073.0 }, { "bucket": 14176.0, "duration_ms": 10128.805941, "eligible_miss": 0.0, "miss": 9.0, "model": 64.0, "overflow": 9.0, "padding": 15.0, "tokens": 80561.0 }, { "bucket": 14192.0, "duration_ms": 10116.131985000002, "eligible_miss": 0.0, "miss": 9.0, "model": 64.0, "overflow": 9.0, "padding": 14.0, "tokens": 80483.0 }, { "bucket": 13768.0, "duration_ms": 9503.189379, "eligible_miss": 0.0, "miss": 9.0, "model": 63.0, "overflow": 9.0, "padding": 15.0, "tokens": 73874.0 }, { "bucket": 12032.0, "duration_ms": 9550.747098, "eligible_miss": 0.0, "miss": 8.0, "model": 55.0, "overflow": 8.0, "padding": 0.0, "tokens": 74799.0 }, { "bucket": 9160.0, "duration_ms": 9953.987155999997, "eligible_miss": 0.0, "miss": 12.0, "model": 48.0, "overflow": 12.0, "padding": 14.0, "tokens": 87139.0 }, { "bucket": 7368.0, "duration_ms": 10039.995024, "eligible_miss": 0.0, "miss": 12.0, "model": 41.0, "overflow": 12.0, "padding": 14.0, "tokens": 91397.0 }, { "bucket": 13192.0, "duration_ms": 10544.197295000002, "eligible_miss": 0.0, "miss": 10.0, "model": 61.0, "overflow": 10.0, "padding": 17.0, "tokens": 89660.0 }, { "bucket": 13768.0, "duration_ms": 10257.515040999997, "eligible_miss": 0.0, "miss": 10.0, "model": 64.0, "overflow": 10.0, "padding": 14.0, "tokens": 82262.0 }, { "bucket": 13768.0, "duration_ms": 9520.285963, "eligible_miss": 0.0, "miss": 9.0, "model": 63.0, "overflow": 9.0, "padding": 14.0, "tokens": 73873.0 }, { "bucket": 14024.0, "duration_ms": 10389.161113000004, "eligible_miss": 0.0, "miss": 10.0, "model": 64.0, "overflow": 10.0, "padding": 15.0, "tokens": 82860.0 }, { "bucket": 11264.0, "duration_ms": 9225.102485, "eligible_miss": 0.0, "miss": 9.0, "model": 53.0, "overflow": 9.0, "padding": 0.0, "tokens": 72871.0 }, { "bucket": 6360.0, "duration_ms": 10000.893427, "eligible_miss": 0.0, "miss": 13.0, "model": 38.0, "overflow": 13.0, "padding": 2.0, "tokens": 91753.0 }, { "bucket": 9432.0, "duration_ms": 10636.165116999997, "eligible_miss": 0.0, "miss": 13.0, "model": 50.0, "overflow": 13.0, "padding": 2.0, "tokens": 93649.0 }, { "bucket": 13528.0, "duration_ms": 9840.476839, "eligible_miss": 0.0, "miss": 10.0, "model": 63.0, "overflow": 10.0, "padding": 2.0, "tokens": 79400.0 }, { "bucket": 13528.0, "duration_ms": 10080.211508999999, "eligible_miss": 0.0, "miss": 11.0, "model": 64.0, "overflow": 11.0, "padding": 2.0, "tokens": 80608.0 }, { "bucket": 14056.0, "duration_ms": 9981.313267000001, "eligible_miss": 0.0, "miss": 10.0, "model": 64.0, "overflow": 10.0, "padding": 2.0, "tokens": 78511.0 }, { "bucket": 13304.0, "duration_ms": 9443.992412999998, "eligible_miss": 0.0, "miss": 8.0, "model": 60.0, "overflow": 8.0, "padding": 2.0, "tokens": 70921.0 }, { "bucket": 6128.0, "duration_ms": 9931.941679999996, "eligible_miss": 0.0, "miss": 13.0, "model": 37.0, "overflow": 13.0, "padding": 0.0, "tokens": 92355.0 } ], "clean": { "admitted": 10392, "completed": 10392, "completed_throughput_rps": 43.3, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 3310593, "offered_rps": 43.3, "output_tokens": 665088, "start_s": 60.0 }, "config": "C00", "drain_quarantined": false, "drain_seconds": 2.2563367690017913, "latency_s": { "e2e": { "mean": 5.900970134643903, "n": 10392, "p50": 5.894884387002094, "p95": 6.19822557131265, "p99": 6.350330786115083 }, "tpot": { "mean": 0.07734891378714435, "n": 10392, "p50": 0.07630683034117933, "p95": 0.08648301882954362, "p99": 0.08921301509375178 }, "ttft": { "mean": 1.0279885660538086, "n": 10392, "p50": 1.0842870905034943, "p95": 1.5127993570451501, "p99": 1.5493279498213086 } }, "layer1": { "decode_tokens": 652646, "kv_usage_max": 0.3451743714517437, "kv_usage_mean": 0.304654382467603, "mode_counts": { "FULL": 2164, "NONE": 498, "PIECEWISE": 13 }, "mode_shares": { "FULL": 0.8089719626168225, "NONE": 0.18616822429906543, "PIECEWISE": 0.00485981308411215 }, "preemptions": 0, "prefill_tokens": 3323073, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 23, "queue_waiting_mean": 0.2680373831775701, "records_all": 4187, "records_clean": 2675, "requests_per_step": { "mean": 247.93570093457944, "n": 2675, "p50": 256.0, "p95": 256.0, "p99": 256.0 }, "scheduled_tokens_per_step": { "mean": 1486.2500934579439, "n": 2675, "p50": 256.0, "p95": 8192.0, "p99": 8192.0 }, "step_duration_ms": { "mean": 179.15588237308413, "n": 2675, "p50": 70.26221, "p95": 757.4315151999998, "p99": 772.54264124 }, "token_efficiency_per_ms": 8.29584869763246 }, "layer2_missing_after_controller_cleanup": false, "load": "saturation", "pattern": "P01", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 41.35, "clean_c_waiting_median": 0.0, "completion_rate_rps": 36.7, "completion_rate_within_10pct": false, "tail_end_s": 337.969882845995, "tail_start_s": 327.969882845995, "valid": false, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 41.35, "clean_c_waiting_median": 0.0, "completion_rate_rps": 38.8, "completion_rate_within_10pct": true, "tail_end_s": 392.74431553299655, "tail_start_s": 382.74431553299655, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 10392, "run_dir": "runs/phase3/primary/P01-C00/saturation", "run_id": "P01-C00-saturation", "trace_files": 2, "waste": { "R128": 0.3723323346172142, "R32": 0.3612776759520059, "R64": 0.36868249852408347, "bucket_slack": 0.0008228755826461097, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.18616822429906543, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.18616822429906543, "padded_tokens_per_useful_token": 0.00011545081531164552, "padding_fraction": 0.0008228755826461097 } }, "P01-C01-moderate": { "blocks": [ { "bucket": 33608.0, "duration_ms": 9997.635068999996, "eligible_miss": 0.0, "miss": 23.0, "model": 140.0, "overflow": 23.0, "padding": 680.0, "tokens": 46601.0 }, { "bucket": 37032.0, "duration_ms": 9961.48037, "eligible_miss": 0.0, "miss": 19.0, "model": 133.0, "overflow": 19.0, "padding": 670.0, "tokens": 47088.0 }, { "bucket": 35760.0, "duration_ms": 10047.266813000002, "eligible_miss": 0.0, "miss": 20.0, "model": 137.0, "overflow": 20.0, "padding": 683.0, "tokens": 46599.0 }, { "bucket": 35280.0, "duration_ms": 9931.102751999999, "eligible_miss": 0.0, "miss": 20.0, "model": 137.0, "overflow": 20.0, "padding": 695.0, "tokens": 45552.0 }, { "bucket": 32384.0, "duration_ms": 10010.852824999993, "eligible_miss": 0.0, "miss": 28.0, "model": 133.0, "overflow": 28.0, "padding": 596.0, "tokens": 47714.0 }, { "bucket": 35808.0, "duration_ms": 9985.833894000005, "eligible_miss": 0.0, "miss": 18.0, "model": 141.0, "overflow": 18.0, "padding": 696.0, "tokens": 44852.0 }, { "bucket": 34440.0, "duration_ms": 9966.572230000005, "eligible_miss": 0.0, "miss": 22.0, "model": 138.0, "overflow": 22.0, "padding": 753.0, "tokens": 46096.0 }, { "bucket": 36392.0, "duration_ms": 10001.279647999996, "eligible_miss": 0.0, "miss": 16.0, "model": 145.0, "overflow": 16.0, "padding": 671.0, "tokens": 44970.0 }, { "bucket": 36648.0, "duration_ms": 10050.746529000007, "eligible_miss": 0.0, "miss": 18.0, "model": 144.0, "overflow": 18.0, "padding": 756.0, "tokens": 46045.0 }, { "bucket": 36416.0, "duration_ms": 9897.770381000002, "eligible_miss": 0.0, "miss": 17.0, "model": 137.0, "overflow": 17.0, "padding": 703.0, "tokens": 45233.0 }, { "bucket": 34080.0, "duration_ms": 10010.004142999991, "eligible_miss": 0.0, "miss": 24.0, "model": 131.0, "overflow": 24.0, "padding": 737.0, "tokens": 47680.0 }, { "bucket": 36512.0, "duration_ms": 10016.691993000004, "eligible_miss": 0.0, "miss": 18.0, "model": 144.0, "overflow": 18.0, "padding": 656.0, "tokens": 46337.0 }, { "bucket": 34792.0, "duration_ms": 9929.375679999992, "eligible_miss": 0.0, "miss": 20.0, "model": 141.0, "overflow": 20.0, "padding": 690.0, "tokens": 45587.0 }, { "bucket": 31120.0, "duration_ms": 10033.621968, "eligible_miss": 0.0, "miss": 31.0, "model": 130.0, "overflow": 31.0, "padding": 628.0, "tokens": 48792.0 }, { "bucket": 34576.0, "duration_ms": 9930.906926000003, "eligible_miss": 0.0, "miss": 24.0, "model": 129.0, "overflow": 24.0, "padding": 732.0, "tokens": 48000.0 }, { "bucket": 36664.0, "duration_ms": 10031.479860999998, "eligible_miss": 0.0, "miss": 19.0, "model": 135.0, "overflow": 19.0, "padding": 692.0, "tokens": 46562.0 }, { "bucket": 33376.0, "duration_ms": 9948.186458999993, "eligible_miss": 0.0, "miss": 24.0, "model": 135.0, "overflow": 24.0, "padding": 727.0, "tokens": 46551.0 }, { "bucket": 36848.0, "duration_ms": 10050.385339000004, "eligible_miss": 0.0, "miss": 18.0, "model": 140.0, "overflow": 18.0, "padding": 711.0, "tokens": 46130.0 }, { "bucket": 35712.0, "duration_ms": 9975.735268999999, "eligible_miss": 0.0, "miss": 21.0, "model": 136.0, "overflow": 21.0, "padding": 695.0, "tokens": 46545.0 }, { "bucket": 33352.0, "duration_ms": 9940.775106000003, "eligible_miss": 0.0, "miss": 26.0, "model": 130.0, "overflow": 26.0, "padding": 682.0, "tokens": 46963.0 }, { "bucket": 34840.0, "duration_ms": 9966.589301999995, "eligible_miss": 0.0, "miss": 22.0, "model": 141.0, "overflow": 22.0, "padding": 690.0, "tokens": 46120.0 }, { "bucket": 34928.0, "duration_ms": 9994.235396, "eligible_miss": 0.0, "miss": 22.0, "model": 141.0, "overflow": 22.0, "padding": 747.0, "tokens": 46500.0 }, { "bucket": 36512.0, "duration_ms": 10025.756066000002, "eligible_miss": 0.0, "miss": 18.0, "model": 138.0, "overflow": 18.0, "padding": 722.0, "tokens": 47204.0 }, { "bucket": 33312.0, "duration_ms": 9926.436303000002, "eligible_miss": 0.0, "miss": 26.0, "model": 128.0, "overflow": 26.0, "padding": 617.0, "tokens": 48076.0 }, { "bucket": 35520.0, "duration_ms": 10003.942259999994, "eligible_miss": 0.0, "miss": 21.0, "model": 139.0, "overflow": 21.0, "padding": 715.0, "tokens": 46573.0 }, { "bucket": 32648.0, "duration_ms": 9988.033101000003, "eligible_miss": 0.0, "miss": 22.0, "model": 147.0, "overflow": 22.0, "padding": 694.0, "tokens": 44739.0 }, { "bucket": 35728.0, "duration_ms": 10012.5605, "eligible_miss": 0.0, "miss": 22.0, "model": 134.0, "overflow": 22.0, "padding": 742.0, "tokens": 47332.0 }, { "bucket": 40168.0, "duration_ms": 9936.560732999998, "eligible_miss": 0.0, "miss": 11.0, "model": 136.0, "overflow": 11.0, "padding": 755.0, "tokens": 45670.0 }, { "bucket": 34392.0, "duration_ms": 10016.966579000002, "eligible_miss": 0.0, "miss": 27.0, "model": 124.0, "overflow": 27.0, "padding": 694.0, "tokens": 48772.0 }, { "bucket": 35208.0, "duration_ms": 10000.276685000003, "eligible_miss": 0.0, "miss": 18.0, "model": 146.0, "overflow": 18.0, "padding": 687.0, "tokens": 45124.0 }, { "bucket": 35912.0, "duration_ms": 9956.369649000004, "eligible_miss": 0.0, "miss": 16.0, "model": 145.0, "overflow": 16.0, "padding": 730.0, "tokens": 44880.0 }, { "bucket": 38944.0, "duration_ms": 10032.647223000002, "eligible_miss": 0.0, "miss": 13.0, "model": 144.0, "overflow": 13.0, "padding": 751.0, "tokens": 45459.0 }, { "bucket": 38576.0, "duration_ms": 9961.166588000004, "eligible_miss": 0.0, "miss": 15.0, "model": 136.0, "overflow": 15.0, "padding": 726.0, "tokens": 46648.0 }, { "bucket": 34832.0, "duration_ms": 9956.285011999998, "eligible_miss": 0.0, "miss": 22.0, "model": 132.0, "overflow": 22.0, "padding": 703.0, "tokens": 46455.0 }, { "bucket": 34768.0, "duration_ms": 10025.576010999996, "eligible_miss": 0.0, "miss": 24.0, "model": 130.0, "overflow": 24.0, "padding": 710.0, "tokens": 47930.0 }, { "bucket": 37920.0, "duration_ms": 9986.476466, "eligible_miss": 0.0, "miss": 15.0, "model": 142.0, "overflow": 15.0, "padding": 785.0, "tokens": 45329.0 }, { "bucket": 36936.0, "duration_ms": 9928.282509000004, "eligible_miss": 0.0, "miss": 17.0, "model": 139.0, "overflow": 17.0, "padding": 750.0, "tokens": 45710.0 }, { "bucket": 35872.0, "duration_ms": 10044.772734000007, "eligible_miss": 0.0, "miss": 23.0, "model": 129.0, "overflow": 23.0, "padding": 702.0, "tokens": 48508.0 }, { "bucket": 37512.0, "duration_ms": 9915.907078000002, "eligible_miss": 0.0, "miss": 17.0, "model": 131.0, "overflow": 17.0, "padding": 709.0, "tokens": 45909.0 }, { "bucket": 40648.0, "duration_ms": 9987.487444, "eligible_miss": 0.0, "miss": 8.0, "model": 146.0, "overflow": 8.0, "padding": 845.0, "tokens": 44254.0 }, { "bucket": 38336.0, "duration_ms": 10042.002508, "eligible_miss": 0.0, "miss": 12.0, "model": 149.0, "overflow": 12.0, "padding": 796.0, "tokens": 45324.0 }, { "bucket": 36144.0, "duration_ms": 9982.605775999999, "eligible_miss": 0.0, "miss": 19.0, "model": 141.0, "overflow": 19.0, "padding": 816.0, "tokens": 45801.0 }, { "bucket": 31264.0, "duration_ms": 9969.342419999999, "eligible_miss": 0.0, "miss": 30.0, "model": 130.0, "overflow": 30.0, "padding": 591.0, "tokens": 47244.0 }, { "bucket": 33888.0, "duration_ms": 9940.104527999998, "eligible_miss": 0.0, "miss": 18.0, "model": 149.0, "overflow": 18.0, "padding": 751.0, "tokens": 44902.0 }, { "bucket": 35936.0, "duration_ms": 10048.677680999996, "eligible_miss": 0.0, "miss": 20.0, "model": 140.0, "overflow": 20.0, "padding": 727.0, "tokens": 45967.0 }, { "bucket": 40856.0, "duration_ms": 9962.541356000005, "eligible_miss": 0.0, "miss": 8.0, "model": 141.0, "overflow": 8.0, "padding": 765.0, "tokens": 44470.0 }, { "bucket": 36200.0, "duration_ms": 9954.206755000001, "eligible_miss": 0.0, "miss": 16.0, "model": 144.0, "overflow": 16.0, "padding": 699.0, "tokens": 44968.0 }, { "bucket": 33544.0, "duration_ms": 10076.081104, "eligible_miss": 0.0, "miss": 24.0, "model": 140.0, "overflow": 24.0, "padding": 648.0, "tokens": 46552.0 } ], "clean": { "admitted": 5828, "completed": 5828, "completed_throughput_rps": 24.283333333333335, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 1855465, "offered_rps": 24.283333333333335, "output_tokens": 372992, "start_s": 60.0 }, "config": "C01", "drain_quarantined": false, "drain_seconds": 0.9099243679956999, "latency_s": { "e2e": { "mean": 2.385056775077354, "n": 5828, "p50": 2.3748430520063266, "p95": 2.627926318097161, "p99": 2.698679346006247 }, "tpot": { "mean": 0.03631807814162525, "n": 5828, "p50": 0.036205446753661996, "p95": 0.04003349922697655, "p99": 0.041193774410538245 }, "ttft": { "mean": 0.09701785215496304, "n": 5828, "p50": 0.09653152749524452, "p95": 0.12175093539408405, "p99": 0.13423520062555325 } }, "layer1": { "decode_tokens": 367220, "kv_usage_max": 0.08770714552139391, "kv_usage_mean": 0.06821269396718065, "mode_counts": { "FULL": 968, "NONE": 952, "PIECEWISE": 4698 }, "mode_shares": { "FULL": 0.1462677546086431, "NONE": 0.1438501057721366, "PIECEWISE": 0.7098821396192203 }, "preemptions": 0, "prefill_tokens": 1855097, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 0, "queue_waiting_mean": 0.0, "records_all": 9535, "records_clean": 6618, "requests_per_step": { "mean": 56.368691447567244, "n": 6618, "p50": 56.0, "p95": 62.0, "p99": 64.0 }, "scheduled_tokens_per_step": { "mean": 335.7988818374131, "n": 6618, "p50": 345.0, "p95": 555.0, "p99": 758.6599999999999 }, "step_duration_ms": { "mean": 72.43269764611665, "n": 6618, "p50": 73.99482599999999, "p95": 92.3781244, "p99": 96.50266256 }, "token_efficiency_per_ms": 4.636012363891521 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P01", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 24.05, "clean_c_waiting_median": 0.0, "completion_rate_rps": 25.5, "completion_rate_within_10pct": true, "tail_end_s": 343.72796904700226, "tail_start_s": 333.72796904700226, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 24.05, "clean_c_waiting_median": 0.0, "completion_rate_rps": 23.8, "completion_rate_within_10pct": true, "tail_end_s": 384.0086190129805, "tail_start_s": 374.0086190129805, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": true, "requests_completed": 5828, "run_dir": "runs/phase3/primary/P01-C01/moderate", "run_id": "P01-C01-moderate", "trace_files": 2, "waste": { "R128": 0.3723323346172142, "R32": 0.3612776759520059, "R64": 0.36868249852408347, "bucket_slack": 0.01992823033576615, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.1438501057721366, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 5650, "moe_layer_cv": null, "overflow_rate": 0.1438501057721366, "padded_tokens_per_useful_token": 0.01535334517982808, "padding_fraction": 0.01992823033576615 } }, "P01-C01-saturation": { "blocks": [ { "bucket": 4000.0, "duration_ms": 10203.605463999998, "eligible_miss": 0.0, "miss": 41.0, "model": 56.0, "overflow": 41.0, "padding": 15.0, "tokens": 78120.0 }, { "bucket": 4016.0, "duration_ms": 9742.766153999997, "eligible_miss": 0.0, "miss": 39.0, "model": 54.0, "overflow": 39.0, "padding": 21.0, "tokens": 73810.0 }, { "bucket": 1536.0, "duration_ms": 9918.749321999998, "eligible_miss": 0.0, "miss": 41.0, "model": 47.0, "overflow": 41.0, "padding": 0.0, "tokens": 78980.0 }, { "bucket": 2048.0, "duration_ms": 10299.614912999996, "eligible_miss": 0.0, "miss": 42.0, "model": 50.0, "overflow": 42.0, "padding": 6.0, "tokens": 82678.0 }, { "bucket": 4016.0, "duration_ms": 9787.362490000001, "eligible_miss": 0.0, "miss": 39.0, "model": 54.0, "overflow": 39.0, "padding": 9.0, "tokens": 74464.0 }, { "bucket": 4096.0, "duration_ms": 10124.917670999996, "eligible_miss": 0.0, "miss": 41.0, "model": 56.0, "overflow": 41.0, "padding": 10.0, "tokens": 76877.0 }, { "bucket": 3584.0, "duration_ms": 9860.220744000002, "eligible_miss": 0.0, "miss": 39.0, "model": 53.0, "overflow": 39.0, "padding": 6.0, "tokens": 75880.0 }, { "duration_ms": 10018.159282, "eligible_miss": 0.0, "miss": 44.0, "model": 44.0, "overflow": 44.0, "tokens": 81806.0 }, { "bucket": 3584.0, "duration_ms": 9971.427643, "eligible_miss": 0.0, "miss": 40.0, "model": 54.0, "overflow": 40.0, "padding": 6.0, "tokens": 76676.0 }, { "bucket": 3728.0, "duration_ms": 9969.959431999998, "eligible_miss": 0.0, "miss": 40.0, "model": 54.0, "overflow": 40.0, "padding": 6.0, "tokens": 75907.0 }, { "bucket": 3328.0, "duration_ms": 10025.561862000004, "eligible_miss": 0.0, "miss": 42.0, "model": 55.0, "overflow": 42.0, "padding": 6.0, "tokens": 76352.0 }, { "bucket": 3328.0, "duration_ms": 10026.678248000002, "eligible_miss": 0.0, "miss": 41.0, "model": 54.0, "overflow": 41.0, "padding": 6.0, "tokens": 77493.0 }, { "duration_ms": 9922.874876999997, "eligible_miss": 0.0, "miss": 44.0, "model": 44.0, "overflow": 44.0, "tokens": 80650.0 }, { "bucket": 3744.0, "duration_ms": 10141.583717000001, "eligible_miss": 0.0, "miss": 42.0, "model": 56.0, "overflow": 42.0, "padding": 7.0, "tokens": 77129.0 }, { "bucket": 3328.0, "duration_ms": 9825.641666, "eligible_miss": 0.0, "miss": 41.0, "model": 54.0, "overflow": 41.0, "padding": 6.0, "tokens": 74853.0 }, { "bucket": 3328.0, "duration_ms": 10026.996974, "eligible_miss": 0.0, "miss": 41.0, "model": 54.0, "overflow": 41.0, "padding": 6.0, "tokens": 76782.0 }, { "bucket": 3456.0, "duration_ms": 9989.331988000002, "eligible_miss": 0.0, "miss": 41.0, "model": 54.0, "overflow": 41.0, "padding": 13.0, "tokens": 76731.0 }, { "duration_ms": 10182.908675999997, "eligible_miss": 0.0, "miss": 45.0, "model": 45.0, "overflow": 45.0, "tokens": 83111.0 }, { "bucket": 3072.0, "duration_ms": 9888.974163999997, "eligible_miss": 0.0, "miss": 43.0, "model": 55.0, "overflow": 43.0, "padding": 6.0, "tokens": 74301.0 }, { "bucket": 3488.0, "duration_ms": 9964.314148999998, "eligible_miss": 0.0, "miss": 43.0, "model": 56.0, "overflow": 43.0, "padding": 14.0, "tokens": 75363.0 }, { "bucket": 3072.0, "duration_ms": 9960.435744000002, "eligible_miss": 0.0, "miss": 41.0, "model": 53.0, "overflow": 41.0, "padding": 6.0, "tokens": 76792.0 }, { "bucket": 2816.0, "duration_ms": 9875.558238, "eligible_miss": 0.0, "miss": 41.0, "model": 52.0, "overflow": 41.0, "padding": 1.0, "tokens": 75921.0 }, { "bucket": 704.0, "duration_ms": 10072.600117999998, "eligible_miss": 0.0, "miss": 47.0, "model": 49.0, "overflow": 47.0, "padding": 11.0, "tokens": 79977.0 }, { "bucket": 3072.0, "duration_ms": 10144.145703000002, "eligible_miss": 0.0, "miss": 43.0, "model": 55.0, "overflow": 43.0, "padding": 6.0, "tokens": 77811.0 }, { "bucket": 3072.0, "duration_ms": 10003.565046, "eligible_miss": 0.0, "miss": 41.0, "model": 53.0, "overflow": 41.0, "padding": 6.0, "tokens": 76865.0 }, { "bucket": 3776.0, "duration_ms": 9818.520830000003, "eligible_miss": 0.0, "miss": 40.0, "model": 53.0, "overflow": 40.0, "padding": 20.0, "tokens": 74777.0 }, { "bucket": 768.0, "duration_ms": 9910.496845, "eligible_miss": 0.0, "miss": 44.0, "model": 47.0, "overflow": 44.0, "padding": 0.0, "tokens": 78154.0 }, { "bucket": 2496.0, "duration_ms": 10102.562553000002, "eligible_miss": 0.0, "miss": 45.0, "model": 54.0, "overflow": 45.0, "padding": 9.0, "tokens": 78424.0 }, { "bucket": 3216.0, "duration_ms": 9924.138751, "eligible_miss": 0.0, "miss": 42.0, "model": 54.0, "overflow": 42.0, "padding": 7.0, "tokens": 75864.0 }, { "bucket": 2816.0, "duration_ms": 10187.513168, "eligible_miss": 0.0, "miss": 44.0, "model": 55.0, "overflow": 44.0, "padding": 6.0, "tokens": 77625.0 }, { "bucket": 3328.0, "duration_ms": 9789.426399000002, "eligible_miss": 0.0, "miss": 40.0, "model": 52.0, "overflow": 40.0, "padding": 6.0, "tokens": 74936.0 }, { "duration_ms": 10114.070901, "eligible_miss": 0.0, "miss": 46.0, "model": 46.0, "overflow": 46.0, "tokens": 81214.0 }, { "bucket": 2816.0, "duration_ms": 10088.948949999998, "eligible_miss": 0.0, "miss": 44.0, "model": 55.0, "overflow": 44.0, "padding": 6.0, "tokens": 76677.0 }, { "bucket": 3232.0, "duration_ms": 9866.455802, "eligible_miss": 0.0, "miss": 42.0, "model": 54.0, "overflow": 42.0, "padding": 19.0, "tokens": 74833.0 }, { "bucket": 3264.0, "duration_ms": 9894.975111999998, "eligible_miss": 0.0, "miss": 42.0, "model": 54.0, "overflow": 42.0, "padding": 21.0, "tokens": 74962.0 }, { "bucket": 3072.0, "duration_ms": 10085.450928999997, "eligible_miss": 0.0, "miss": 42.0, "model": 53.0, "overflow": 42.0, "padding": 13.0, "tokens": 78380.0 }, { "duration_ms": 10046.627470999998, "eligible_miss": 0.0, "miss": 45.0, "model": 45.0, "overflow": 45.0, "tokens": 81298.0 }, { "bucket": 2560.0, "duration_ms": 9847.101603000001, "eligible_miss": 0.0, "miss": 45.0, "model": 55.0, "overflow": 45.0, "padding": 6.0, "tokens": 73217.0 }, { "bucket": 2560.0, "duration_ms": 10024.588917, "eligible_miss": 0.0, "miss": 45.0, "model": 55.0, "overflow": 45.0, "padding": 6.0, "tokens": 76246.0 }, { "bucket": 3008.0, "duration_ms": 9929.563581000004, "eligible_miss": 0.0, "miss": 42.0, "model": 53.0, "overflow": 42.0, "padding": 17.0, "tokens": 75777.0 }, { "bucket": 2560.0, "duration_ms": 10077.664327000002, "eligible_miss": 0.0, "miss": 44.0, "model": 54.0, "overflow": 44.0, "padding": 6.0, "tokens": 76980.0 }, { "duration_ms": 9992.777184999997, "eligible_miss": 0.0, "miss": 46.0, "model": 46.0, "overflow": 46.0, "tokens": 80209.0 }, { "bucket": 2560.0, "duration_ms": 10091.163340000003, "eligible_miss": 0.0, "miss": 43.0, "model": 53.0, "overflow": 43.0, "padding": 6.0, "tokens": 77665.0 }, { "bucket": 3072.0, "duration_ms": 9848.346787, "eligible_miss": 0.0, "miss": 43.0, "model": 54.0, "overflow": 43.0, "padding": 15.0, "tokens": 74253.0 }, { "bucket": 2560.0, "duration_ms": 10082.291702, "eligible_miss": 0.0, "miss": 45.0, "model": 55.0, "overflow": 45.0, "padding": 6.0, "tokens": 76492.0 }, { "bucket": 2048.0, "duration_ms": 9842.737886000003, "eligible_miss": 0.0, "miss": 41.0, "model": 48.0, "overflow": 41.0, "padding": 6.0, "tokens": 77465.0 }, { "bucket": 768.0, "duration_ms": 10038.773943999997, "eligible_miss": 0.0, "miss": 47.0, "model": 50.0, "overflow": 47.0, "padding": 6.0, "tokens": 78339.0 }, { "bucket": 2304.0, "duration_ms": 10092.552672000002, "eligible_miss": 0.0, "miss": 45.0, "model": 54.0, "overflow": 45.0, "padding": 6.0, "tokens": 76729.0 } ], "clean": { "admitted": 9713, "completed": 9713, "completed_throughput_rps": 40.47083333333333, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 3091454, "offered_rps": 40.47083333333333, "output_tokens": 621632, "start_s": 60.0 }, "config": "C01", "drain_quarantined": false, "drain_seconds": 2.0416924619930796, "latency_s": { "e2e": { "mean": 6.321913773528025, "n": 9713, "p50": 6.324586006987374, "p95": 6.48759062900208, "p99": 6.554015111649641 }, "tpot": { "mean": 0.09486961022559012, "n": 9713, "p50": 0.09484719088909009, "p95": 0.09758893054289122, "p99": 0.09857375903008876 }, "ttft": { "mean": 0.34512832931584686, "n": 9713, "p50": 0.33935471798758954, "p95": 0.4816830246010795, "p99": 0.4956150398438331 } }, "layer1": { "decode_tokens": 612439, "kv_usage_max": 0.3233335109500719, "kv_usage_mean": 0.3000972717007496, "mode_counts": { "FULL": 445, "NONE": 2044, "PIECEWISE": 21 }, "mode_shares": { "FULL": 0.17729083665338646, "NONE": 0.8143426294820717, "PIECEWISE": 0.008366533864541833 }, "preemptions": 0, "prefill_tokens": 3093406, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 5, "queue_waiting_mean": 0.13266932270916335, "records_all": 3944, "records_clean": 2510, "requests_per_step": { "mean": 248.12749003984064, "n": 2510, "p50": 247.0, "p95": 256.0, "p99": 256.0 }, "scheduled_tokens_per_step": { "mean": 1476.4322709163346, "n": 2510, "p50": 1699.5, "p95": 2048.0, "p99": 2048.0 }, "step_duration_ms": { "mean": 191.09350754581675, "n": 2510, "p50": 213.4761155, "p95": 245.4417175, "p99": 246.39050363 }, "token_efficiency_per_ms": 7.726229372614054 }, "layer2_missing_after_controller_cleanup": false, "load": "saturation", "pattern": "P01", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 40.05, "clean_c_waiting_median": 0.0, "completion_rate_rps": 41.2, "completion_rate_within_10pct": true, "tail_end_s": 353.45747823201236, "tail_start_s": 343.45747823201236, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 40.05, "clean_c_waiting_median": 0.0, "completion_rate_rps": 42.8, "completion_rate_within_10pct": true, "tail_end_s": 391.7979503819952, "tail_start_s": 381.7979503819952, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": true, "requests_completed": 9713, "run_dir": "runs/phase3/primary/P01-C01/saturation", "run_id": "P01-C01-saturation", "trace_files": 2, "waste": { "R128": 0.3723323346172142, "R32": 0.3612776759520059, "R64": 0.36868249852408347, "bucket_slack": 0.002922077922077922, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.8143426294820717, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.8143426294820717, "padded_tokens_per_useful_token": 9.714383629104834e-05, "padding_fraction": 0.002922077922077922 } }, "P01-C10-moderate": { "blocks": [ { "bucket": 3288.0, "duration_ms": 9949.162208000007, "eligible_miss": 93.0, "miss": 98.0, "model": 193.0, "overflow": 5.0, "padding": 233.0, "tokens": 38451.0 }, { "bucket": 3552.0, "duration_ms": 10012.469207000002, "eligible_miss": 86.0, "miss": 98.0, "model": 195.0, "overflow": 12.0, "padding": 382.0, "tokens": 35916.0 }, { "bucket": 3192.0, "duration_ms": 10035.694512, "eligible_miss": 92.0, "miss": 99.0, "model": 193.0, "overflow": 7.0, "padding": 213.0, "tokens": 37924.0 }, { "bucket": 3168.0, "duration_ms": 9936.948090999995, "eligible_miss": 91.0, "miss": 97.0, "model": 178.0, "overflow": 6.0, "padding": 292.0, "tokens": 37083.0 }, { "bucket": 3184.0, "duration_ms": 10005.574367, "eligible_miss": 92.0, "miss": 99.0, "model": 193.0, "overflow": 7.0, "padding": 209.0, "tokens": 38225.0 }, { "bucket": 3392.0, "duration_ms": 9952.588998999996, "eligible_miss": 94.0, "miss": 98.0, "model": 190.0, "overflow": 4.0, "padding": 363.0, "tokens": 37680.0 }, { "bucket": 3424.0, "duration_ms": 10046.252394999994, "eligible_miss": 86.0, "miss": 99.0, "model": 197.0, "overflow": 13.0, "padding": 277.0, "tokens": 37741.0 }, { "bucket": 3232.0, "duration_ms": 9949.493189000004, "eligible_miss": 89.0, "miss": 98.0, "model": 187.0, "overflow": 9.0, "padding": 325.0, "tokens": 38337.0 }, { "bucket": 3392.0, "duration_ms": 9946.791941, "eligible_miss": 85.0, "miss": 98.0, "model": 186.0, "overflow": 13.0, "padding": 442.0, "tokens": 37613.0 }, { "bucket": 3712.0, "duration_ms": 10000.662096999997, "eligible_miss": 91.0, "miss": 98.0, "model": 202.0, "overflow": 7.0, "padding": 423.0, "tokens": 35782.0 }, { "bucket": 3176.0, "duration_ms": 10035.215516000002, "eligible_miss": 91.0, "miss": 99.0, "model": 196.0, "overflow": 8.0, "padding": 136.0, "tokens": 38369.0 }, { "bucket": 3512.0, "duration_ms": 9896.367080000002, "eligible_miss": 94.0, "miss": 98.0, "model": 201.0, "overflow": 4.0, "padding": 285.0, "tokens": 36488.0 }, { "bucket": 3488.0, "duration_ms": 10034.694095, "eligible_miss": 93.0, "miss": 99.0, "model": 208.0, "overflow": 6.0, "padding": 209.0, "tokens": 36296.0 }, { "bucket": 3472.0, "duration_ms": 9994.456549999997, "eligible_miss": 88.0, "miss": 98.0, "model": 204.0, "overflow": 10.0, "padding": 285.0, "tokens": 37423.0 }, { "bucket": 3528.0, "duration_ms": 9952.904014, "eligible_miss": 89.0, "miss": 98.0, "model": 201.0, "overflow": 9.0, "padding": 267.0, "tokens": 36217.0 }, { "bucket": 3320.0, "duration_ms": 10038.123934000003, "eligible_miss": 86.0, "miss": 99.0, "model": 188.0, "overflow": 13.0, "padding": 397.0, "tokens": 40142.0 }, { "bucket": 3512.0, "duration_ms": 9891.855007000004, "eligible_miss": 94.0, "miss": 98.0, "model": 206.0, "overflow": 4.0, "padding": 189.0, "tokens": 36244.0 }, { "bucket": 3456.0, "duration_ms": 10094.883914000004, "eligible_miss": 93.0, "miss": 99.0, "model": 207.0, "overflow": 6.0, "padding": 165.0, "tokens": 37001.0 }, { "bucket": 3152.0, "duration_ms": 9887.934911, "eligible_miss": 89.0, "miss": 98.0, "model": 194.0, "overflow": 9.0, "padding": 139.0, "tokens": 38069.0 }, { "bucket": 3200.0, "duration_ms": 10016.706595000005, "eligible_miss": 82.0, "miss": 98.0, "model": 181.0, "overflow": 16.0, "padding": 396.0, "tokens": 39585.0 }, { "bucket": 3424.0, "duration_ms": 9978.465713999998, "eligible_miss": 90.0, "miss": 99.0, "model": 199.0, "overflow": 9.0, "padding": 209.0, "tokens": 38571.0 }, { "bucket": 3328.0, "duration_ms": 10008.412338, "eligible_miss": 87.0, "miss": 98.0, "model": 194.0, "overflow": 11.0, "padding": 248.0, "tokens": 38128.0 }, { "bucket": 3472.0, "duration_ms": 9986.329713000001, "eligible_miss": 86.0, "miss": 98.0, "model": 192.0, "overflow": 12.0, "padding": 380.0, "tokens": 37501.0 }, { "bucket": 3312.0, "duration_ms": 9999.963895000003, "eligible_miss": 92.0, "miss": 98.0, "model": 199.0, "overflow": 6.0, "padding": 121.0, "tokens": 37709.0 }, { "bucket": 3296.0, "duration_ms": 9915.257924999994, "eligible_miss": 92.0, "miss": 98.0, "model": 197.0, "overflow": 6.0, "padding": 190.0, "tokens": 37317.0 }, { "bucket": 3328.0, "duration_ms": 10019.317182000004, "eligible_miss": 92.0, "miss": 99.0, "model": 199.0, "overflow": 7.0, "padding": 239.0, "tokens": 37778.0 }, { "bucket": 3408.0, "duration_ms": 9954.582479999997, "eligible_miss": 78.0, "miss": 98.0, "model": 190.0, "overflow": 20.0, "padding": 417.0, "tokens": 38704.0 }, { "bucket": 3576.0, "duration_ms": 9995.198032999995, "eligible_miss": 90.0, "miss": 98.0, "model": 195.0, "overflow": 8.0, "padding": 391.0, "tokens": 37028.0 }, { "bucket": 3360.0, "duration_ms": 10041.384194, "eligible_miss": 89.0, "miss": 99.0, "model": 204.0, "overflow": 10.0, "padding": 129.0, "tokens": 37953.0 }, { "bucket": 3456.0, "duration_ms": 9891.348972, "eligible_miss": 94.0, "miss": 98.0, "model": 206.0, "overflow": 4.0, "padding": 201.0, "tokens": 37175.0 }, { "bucket": 3440.0, "duration_ms": 10036.670303999997, "eligible_miss": 95.0, "miss": 99.0, "model": 202.0, "overflow": 4.0, "padding": 246.0, "tokens": 38169.0 }, { "bucket": 3000.0, "duration_ms": 10017.732388999997, "eligible_miss": 82.0, "miss": 98.0, "model": 186.0, "overflow": 16.0, "padding": 152.0, "tokens": 39972.0 }, { "bucket": 3560.0, "duration_ms": 9940.346816, "eligible_miss": 89.0, "miss": 98.0, "model": 201.0, "overflow": 9.0, "padding": 290.0, "tokens": 37126.0 }, { "bucket": 3392.0, "duration_ms": 9977.342724999999, "eligible_miss": 91.0, "miss": 99.0, "model": 205.0, "overflow": 8.0, "padding": 121.0, "tokens": 37406.0 }, { "bucket": 3400.0, "duration_ms": 9963.435447, "eligible_miss": 90.0, "miss": 98.0, "model": 204.0, "overflow": 8.0, "padding": 218.0, "tokens": 36939.0 }, { "bucket": 3408.0, "duration_ms": 10002.120796, "eligible_miss": 89.0, "miss": 98.0, "model": 201.0, "overflow": 9.0, "padding": 190.0, "tokens": 38084.0 }, { "bucket": 3352.0, "duration_ms": 10038.113201000004, "eligible_miss": 95.0, "miss": 99.0, "model": 196.0, "overflow": 4.0, "padding": 265.0, "tokens": 36938.0 }, { "bucket": 3360.0, "duration_ms": 9896.136273, "eligible_miss": 86.0, "miss": 98.0, "model": 183.0, "overflow": 12.0, "padding": 522.0, "tokens": 39351.0 }, { "bucket": 3640.0, "duration_ms": 10043.925811, "eligible_miss": 93.0, "miss": 99.0, "model": 203.0, "overflow": 6.0, "padding": 316.0, "tokens": 37318.0 }, { "bucket": 3368.0, "duration_ms": 9930.598732000006, "eligible_miss": 92.0, "miss": 98.0, "model": 203.0, "overflow": 6.0, "padding": 160.0, "tokens": 36672.0 }, { "bucket": 3488.0, "duration_ms": 9960.504545000005, "eligible_miss": 90.0, "miss": 98.0, "model": 207.0, "overflow": 8.0, "padding": 208.0, "tokens": 36503.0 }, { "bucket": 3456.0, "duration_ms": 10007.049996999998, "eligible_miss": 93.0, "miss": 98.0, "model": 205.0, "overflow": 5.0, "padding": 237.0, "tokens": 37001.0 }, { "bucket": 3368.0, "duration_ms": 10026.919293, "eligible_miss": 95.0, "miss": 99.0, "model": 202.0, "overflow": 4.0, "padding": 173.0, "tokens": 37171.0 }, { "bucket": 3384.0, "duration_ms": 9957.427777999997, "eligible_miss": 85.0, "miss": 98.0, "model": 194.0, "overflow": 13.0, "padding": 296.0, "tokens": 37784.0 }, { "bucket": 3400.0, "duration_ms": 9986.793976999998, "eligible_miss": 89.0, "miss": 99.0, "model": 193.0, "overflow": 10.0, "padding": 357.0, "tokens": 38402.0 }, { "bucket": 3448.0, "duration_ms": 9952.649881000003, "eligible_miss": 91.0, "miss": 98.0, "model": 193.0, "overflow": 7.0, "padding": 348.0, "tokens": 38642.0 }, { "bucket": 3496.0, "duration_ms": 10045.983043, "eligible_miss": 94.0, "miss": 99.0, "model": 207.0, "overflow": 5.0, "padding": 244.0, "tokens": 37187.0 }, { "bucket": 3376.0, "duration_ms": 10027.000933999987, "eligible_miss": 91.0, "miss": 98.0, "model": 203.0, "overflow": 7.0, "padding": 171.0, "tokens": 36786.0 } ], "clean": { "admitted": 4722, "completed": 4724, "completed_throughput_rps": 19.683333333333334, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 1508829, "offered_rps": 19.675, "output_tokens": 302336, "start_s": 60.0 }, "config": "C10", "drain_quarantined": false, "drain_seconds": 1.5010973710159305, "latency_s": { "e2e": { "mean": 1.6713845360269364, "n": 4724, "p50": 1.6473525780020282, "p95": 1.8364300984874717, "p99": 1.9401714695148982 }, "tpot": { "mean": 0.025415942924051336, "n": 4724, "p50": 0.025119858555540088, "p95": 0.02806124114468398, "p99": 0.029400235347168884 }, "ttft": { "mean": 0.07018013181170209, "n": 4724, "p50": 0.06350497498351615, "p95": 0.10228192825015867, "p99": 0.11306477584934285 } }, "layer1": { "decode_tokens": 297570, "kv_usage_max": 0.050254770706364305, "kv_usage_mean": 0.03635361272181466, "mode_counts": { "FULL": 4743, "NONE": 4720 }, "mode_shares": { "FULL": 0.5012152594314699, "NONE": 0.49878474056853006 }, "preemptions": 0, "prefill_tokens": 1508331, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 0, "queue_waiting_mean": 0.0, "records_all": 13476, "records_clean": 9463, "requests_per_step": { "mean": 31.94462643981824, "n": 9463, "p50": 32.0, "p95": 35.0, "p99": 37.0 }, "scheduled_tokens_per_step": { "mean": 190.83810630878156, "n": 9463, "p50": 41.0, "p95": 507.0, "p99": 536.0 }, "step_duration_ms": { "mean": 50.647764029377576, "n": 9463, "p50": 51.929055, "p95": 80.0764609, "p99": 87.45197215999991 }, "token_efficiency_per_ms": 3.7679473115158335 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P01", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 19.65, "clean_c_waiting_median": 0.0, "completion_rate_rps": 26.2, "completion_rate_within_10pct": false, "tail_end_s": 347.5101968499948, "tail_start_s": 337.5101968499948, "valid": false, "waiting_median": 86.0, "waiting_within_10pct": false, "window": 1 }, { "clean_c_completion_rate_median_rps": 19.65, "clean_c_waiting_median": 0.0, "completion_rate_rps": 26.4, "completion_rate_within_10pct": false, "tail_end_s": 388.53855585400015, "tail_start_s": 378.53855585400015, "valid": false, "waiting_median": 51.0, "waiting_within_10pct": false, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 4724, "run_dir": "runs/phase3/primary/P01-C10/moderate", "run_id": "P01-C10-moderate", "trace_files": 2, "waste": { "R128": 0.3723323346172142, "R32": 0.3612776759520059, "R64": 0.36868249852408347, "bucket_slack": 0.024418453716312197, "eligible_miss_rate": 0.45630349783366797, "graph_miss_rate": 0.49878474056853006, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 4720, "moe_layer_cv": null, "overflow_rate": 0.0424812427348621, "padded_tokens_per_useful_token": 0.007013673507019488, "padding_fraction": 0.07787369042349122 } }, "P01-C10-saturation": { "blocks": [ { "bucket": 9600.0, "duration_ms": 9585.937710000002, "eligible_miss": 2.0, "miss": 9.0, "model": 159.0, "overflow": 7.0, "padding": 2.0, "tokens": 56941.0 }, { "bucket": 9920.0, "duration_ms": 10485.887850999992, "eligible_miss": 2.0, "miss": 12.0, "model": 167.0, "overflow": 10.0, "padding": 3.0, "tokens": 69928.0 }, { "bucket": 11200.0, "duration_ms": 9473.565303, "eligible_miss": 2.0, "miss": 8.0, "model": 183.0, "overflow": 6.0, "padding": 2.0, "tokens": 50396.0 }, { "bucket": 8384.0, "duration_ms": 10083.465294000001, "eligible_miss": 3.0, "miss": 12.0, "model": 143.0, "overflow": 9.0, "padding": 3.0, "tokens": 69395.0 }, { "bucket": 11584.0, "duration_ms": 9877.641023000017, "eligible_miss": 2.0, "miss": 8.0, "model": 189.0, "overflow": 6.0, "padding": 2.0, "tokens": 53928.0 }, { "bucket": 8448.0, "duration_ms": 9991.739116999996, "eligible_miss": 2.0, "miss": 12.0, "model": 144.0, "overflow": 10.0, "padding": 3.0, "tokens": 69003.0 }, { "bucket": 11136.0, "duration_ms": 10591.129956999997, "eligible_miss": 2.0, "miss": 11.0, "model": 185.0, "overflow": 9.0, "padding": 3.0, "tokens": 67429.0 }, { "bucket": 8576.0, "duration_ms": 9364.851221999996, "eligible_miss": 2.0, "miss": 9.0, "model": 143.0, "overflow": 7.0, "padding": 2.0, "tokens": 58746.0 }, { "bucket": 10944.0, "duration_ms": 10440.677515000005, "eligible_miss": 3.0, "miss": 11.0, "model": 182.0, "overflow": 8.0, "padding": 3.0, "tokens": 65678.0 }, { "bucket": 9408.0, "duration_ms": 9549.062175999998, "eligible_miss": 2.0, "miss": 9.0, "model": 156.0, "overflow": 7.0, "padding": 2.0, "tokens": 57336.0 }, { "bucket": 10112.0, "duration_ms": 10753.035256000001, "eligible_miss": 3.0, "miss": 12.0, "model": 170.0, "overflow": 9.0, "padding": 3.0, "tokens": 71899.0 }, { "bucket": 10112.0, "duration_ms": 9199.662280000004, "eligible_miss": 2.0, "miss": 8.0, "model": 166.0, "overflow": 6.0, "padding": 2.0, "tokens": 51847.0 }, { "bucket": 9408.0, "duration_ms": 10346.985273999993, "eligible_miss": 3.0, "miss": 12.0, "model": 159.0, "overflow": 9.0, "padding": 3.0, "tokens": 70688.0 }, { "bucket": 11200.0, "duration_ms": 9654.620038999998, "eligible_miss": 2.0, "miss": 8.0, "model": 183.0, "overflow": 6.0, "padding": 2.0, "tokens": 52925.0 }, { "bucket": 8384.0, "duration_ms": 10300.524266999999, "eligible_miss": 3.0, "miss": 12.0, "model": 143.0, "overflow": 9.0, "padding": 3.0, "tokens": 72078.0 }, { "bucket": 11648.0, "duration_ms": 9750.345049999998, "eligible_miss": 2.0, "miss": 9.0, "model": 191.0, "overflow": 7.0, "padding": 3.0, "tokens": 52476.0 }, { "bucket": 8320.0, "duration_ms": 9883.811008, "eligible_miss": 2.0, "miss": 11.0, "model": 141.0, "overflow": 9.0, "padding": 2.0, "tokens": 69969.0 }, { "bucket": 11200.0, "duration_ms": 10627.722131999999, "eligible_miss": 2.0, "miss": 11.0, "model": 186.0, "overflow": 9.0, "padding": 3.0, "tokens": 67543.0 }, { "bucket": 9216.0, "duration_ms": 9352.733858000001, "eligible_miss": 2.0, "miss": 9.0, "model": 153.0, "overflow": 7.0, "padding": 2.0, "tokens": 55624.0 }, { "bucket": 10304.0, "duration_ms": 10591.480396999996, "eligible_miss": 3.0, "miss": 12.0, "model": 173.0, "overflow": 9.0, "padding": 3.0, "tokens": 69690.0 }, { "bucket": 10624.0, "duration_ms": 9384.526043000003, "eligible_miss": 2.0, "miss": 8.0, "model": 174.0, "overflow": 6.0, "padding": 2.0, "tokens": 51441.0 }, { "bucket": 8960.0, "duration_ms": 10530.41977099999, "eligible_miss": 3.0, "miss": 12.0, "model": 152.0, "overflow": 9.0, "padding": 3.0, "tokens": 70762.0 }, { "bucket": 10816.0, "duration_ms": 9433.685700000002, "eligible_miss": 2.0, "miss": 8.0, "model": 177.0, "overflow": 6.0, "padding": 2.0, "tokens": 53860.0 }, { "bucket": 8704.0, "duration_ms": 10167.772811999997, "eligible_miss": 3.0, "miss": 12.0, "model": 148.0, "overflow": 9.0, "padding": 3.0, "tokens": 68677.0 }, { "bucket": 11648.0, "duration_ms": 9886.508919000004, "eligible_miss": 3.0, "miss": 9.0, "model": 191.0, "overflow": 6.0, "padding": 3.0, "tokens": 53558.0 }, { "bucket": 8320.0, "duration_ms": 9885.275682000003, "eligible_miss": 2.0, "miss": 11.0, "model": 141.0, "overflow": 9.0, "padding": 2.0, "tokens": 69626.0 }, { "bucket": 11200.0, "duration_ms": 10338.790289000006, "eligible_miss": 3.0, "miss": 11.0, "model": 186.0, "overflow": 8.0, "padding": 3.0, "tokens": 64514.0 }, { "bucket": 10240.0, "duration_ms": 9647.886849999997, "eligible_miss": 2.0, "miss": 9.0, "model": 169.0, "overflow": 7.0, "padding": 2.0, "tokens": 55945.0 }, { "bucket": 9280.0, "duration_ms": 10466.487114000001, "eligible_miss": 3.0, "miss": 12.0, "model": 157.0, "overflow": 9.0, "padding": 3.0, "tokens": 73136.0 }, { "bucket": 10944.0, "duration_ms": 9522.099796999999, "eligible_miss": 2.0, "miss": 8.0, "model": 179.0, "overflow": 6.0, "padding": 2.0, "tokens": 50955.0 }, { "bucket": 8832.0, "duration_ms": 9977.033838999998, "eligible_miss": 3.0, "miss": 12.0, "model": 150.0, "overflow": 9.0, "padding": 3.0, "tokens": 67514.0 }, { "bucket": 11456.0, "duration_ms": 10609.994196000001, "eligible_miss": 3.0, "miss": 11.0, "model": 190.0, "overflow": 8.0, "padding": 3.0, "tokens": 64182.0 }, { "bucket": 8960.0, "duration_ms": 9355.670728000005, "eligible_miss": 1.0, "miss": 9.0, "model": 149.0, "overflow": 8.0, "padding": 2.0, "tokens": 58884.0 }, { "bucket": 10560.0, "duration_ms": 10406.566008999995, "eligible_miss": 3.0, "miss": 11.0, "model": 176.0, "overflow": 8.0, "padding": 3.0, "tokens": 67259.0 }, { "bucket": 9536.0, "duration_ms": 9561.564771, "eligible_miss": 2.0, "miss": 9.0, "model": 158.0, "overflow": 7.0, "padding": 2.0, "tokens": 57471.0 }, { "bucket": 9984.0, "duration_ms": 10565.880848999994, "eligible_miss": 3.0, "miss": 12.0, "model": 168.0, "overflow": 9.0, "padding": 3.0, "tokens": 70543.0 }, { "bucket": 11008.0, "duration_ms": 9419.635502000005, "eligible_miss": 2.0, "miss": 8.0, "model": 180.0, "overflow": 6.0, "padding": 2.0, "tokens": 50023.0 }, { "bucket": 8576.0, "duration_ms": 9963.122449000006, "eligible_miss": 3.0, "miss": 12.0, "model": 146.0, "overflow": 9.0, "padding": 3.0, "tokens": 68542.0 }, { "bucket": 11648.0, "duration_ms": 10849.752411000003, "eligible_miss": 3.0, "miss": 11.0, "model": 193.0, "overflow": 8.0, "padding": 3.0, "tokens": 68094.0 }, { "bucket": 8576.0, "duration_ms": 9120.307115999996, "eligible_miss": 2.0, "miss": 9.0, "model": 143.0, "overflow": 7.0, "padding": 2.0, "tokens": 56138.0 }, { "bucket": 10944.0, "duration_ms": 10493.4072, "eligible_miss": 3.0, "miss": 11.0, "model": 182.0, "overflow": 8.0, "padding": 3.0, "tokens": 66834.0 }, { "bucket": 9536.0, "duration_ms": 9470.317570000001, "eligible_miss": 2.0, "miss": 9.0, "model": 158.0, "overflow": 7.0, "padding": 2.0, "tokens": 56673.0 }, { "bucket": 9984.0, "duration_ms": 10584.995873, "eligible_miss": 2.0, "miss": 12.0, "model": 168.0, "overflow": 10.0, "padding": 3.0, "tokens": 70791.0 }, { "bucket": 10688.0, "duration_ms": 9395.01719, "eligible_miss": 2.0, "miss": 8.0, "model": 175.0, "overflow": 6.0, "padding": 2.0, "tokens": 51393.0 }, { "bucket": 8896.0, "duration_ms": 10316.016737, "eligible_miss": 3.0, "miss": 12.0, "model": 151.0, "overflow": 9.0, "padding": 3.0, "tokens": 69610.0 }, { "bucket": 11648.0, "duration_ms": 9691.449956999992, "eligible_miss": 2.0, "miss": 8.0, "model": 190.0, "overflow": 6.0, "padding": 3.0, "tokens": 52716.0 }, { "bucket": 8192.0, "duration_ms": 9948.248781, "eligible_miss": 3.0, "miss": 12.0, "model": 140.0, "overflow": 9.0, "padding": 2.0, "tokens": 70776.0 }, { "bucket": 11328.0, "duration_ms": 10753.227755000007, "eligible_miss": 3.0, "miss": 11.0, "model": 188.0, "overflow": 8.0, "padding": 3.0, "tokens": 66675.0 } ], "clean": { "admitted": 7870, "completed": 7870, "completed_throughput_rps": 32.791666666666664, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 2504713, "offered_rps": 32.791666666666664, "output_tokens": 503680, "start_s": 60.0 }, "config": "C10", "drain_quarantined": false, "drain_seconds": 6.23828616499668, "latency_s": { "e2e": { "mean": 7.811715558836478, "n": 7870, "p50": 7.815832740001497, "p95": 7.9524892588422516, "p99": 7.996230083884439 }, "tpot": { "mean": 0.02288580142111304, "n": 7870, "p50": 0.02168167303944568, "p95": 0.02640617163329836, "p99": 0.02914771890473766 }, "ttft": { "mean": 6.369910069306356, "n": 7870, "p50": 6.40973527150345, "p95": 6.6001163164910395, "p99": 6.649974504578276 } }, "layer1": { "decode_tokens": 495936, "kv_usage_max": 0.08457388350484563, "kv_usage_mean": 0.07151143707998636, "mode_counts": { "FULL": 7503, "NONE": 492 }, "mode_shares": { "FULL": 0.9384615384615385, "NONE": 0.06153846153846154 }, "preemptions": 0, "prefill_tokens": 2504175, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 192, "queue_waiting_mean": 191.01563477173232, "records_all": 12286, "records_clean": 7995, "requests_per_step": { "mean": 63.01538461538462, "n": 7995, "p50": 64.0, "p95": 64.0, "p99": 64.0 }, "scheduled_tokens_per_step": { "mean": 375.2484052532833, "n": 7995, "p50": 64.0, "p95": 421.59999999999854, "p99": 7181.0599999999995 }, "step_duration_ms": { "mean": 59.99381346328956, "n": 7995, "p50": 31.676522, "p95": 314.1602991999996, "p99": 626.5985884999999 }, "token_efficiency_per_ms": 6.254785011839584 }, "layer2_missing_after_controller_cleanup": false, "load": "saturation", "pattern": "P01", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 32.0, "clean_c_waiting_median": 192.0, "completion_rate_rps": 32.0, "completion_rate_within_10pct": true, "tail_end_s": 333.5596019870136, "tail_start_s": 323.5596019870136, "valid": true, "waiting_median": 192.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 32.0, "clean_c_waiting_median": 192.0, "completion_rate_rps": 32.1, "completion_rate_within_10pct": true, "tail_end_s": 366.9362416010117, "tail_start_s": 356.9362416010117, "valid": true, "waiting_median": 192.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": true, "requests_completed": 7870, "run_dir": "runs/phase3/primary/P01-C10/saturation", "run_id": "P01-C10-saturation", "trace_files": 2, "waste": { "R128": 0.3723323346172142, "R32": 0.3612776759520059, "R64": 0.36868249852408347, "bucket_slack": 0.0015805949205076409, "eligible_miss_rate": 0.014509068167604753, "graph_miss_rate": 0.06153846153846154, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.047029393370856785, "padded_tokens_per_useful_token": 4.099848305612692e-05, "padding_fraction": 0.00025614754098360657 } }, "P01-C11-moderate": { "blocks": [ { "bucket": 3712.0, "duration_ms": 9959.247200000002, "eligible_miss": 81.0, "miss": 91.0, "model": 207.0, "overflow": 10.0, "padding": 541.0, "tokens": 33619.0 }, { "bucket": 3744.0, "duration_ms": 9977.008518000002, "eligible_miss": 87.0, "miss": 90.0, "model": 207.0, "overflow": 3.0, "padding": 449.0, "tokens": 34868.0 }, { "bucket": 3744.0, "duration_ms": 9948.611453000003, "eligible_miss": 80.0, "miss": 91.0, "model": 208.0, "overflow": 11.0, "padding": 459.0, "tokens": 34053.0 }, { "bucket": 3712.0, "duration_ms": 10087.681306, "eligible_miss": 85.0, "miss": 91.0, "model": 207.0, "overflow": 6.0, "padding": 552.0, "tokens": 34447.0 }, { "bucket": 3744.0, "duration_ms": 9921.699469000001, "eligible_miss": 84.0, "miss": 90.0, "model": 207.0, "overflow": 6.0, "padding": 478.0, "tokens": 34600.0 }, { "bucket": 3616.0, "duration_ms": 9951.080938000001, "eligible_miss": 88.0, "miss": 91.0, "model": 204.0, "overflow": 3.0, "padding": 447.0, "tokens": 33871.0 }, { "bucket": 3520.0, "duration_ms": 10009.982611000001, "eligible_miss": 85.0, "miss": 91.0, "model": 201.0, "overflow": 6.0, "padding": 315.0, "tokens": 35572.0 }, { "bucket": 3584.0, "duration_ms": 9932.805558999993, "eligible_miss": 81.0, "miss": 90.0, "model": 202.0, "overflow": 9.0, "padding": 448.0, "tokens": 34434.0 }, { "bucket": 3744.0, "duration_ms": 10017.269197000005, "eligible_miss": 81.0, "miss": 91.0, "model": 208.0, "overflow": 10.0, "padding": 475.0, "tokens": 34466.0 }, { "bucket": 3616.0, "duration_ms": 9983.475279000002, "eligible_miss": 84.0, "miss": 90.0, "model": 203.0, "overflow": 6.0, "padding": 417.0, "tokens": 34861.0 }, { "bucket": 3680.0, "duration_ms": 10017.097006999997, "eligible_miss": 81.0, "miss": 91.0, "model": 206.0, "overflow": 10.0, "padding": 458.0, "tokens": 35522.0 }, { "bucket": 3808.0, "duration_ms": 9938.864236999998, "eligible_miss": 88.0, "miss": 91.0, "model": 210.0, "overflow": 3.0, "padding": 587.0, "tokens": 33086.0 }, { "bucket": 3552.0, "duration_ms": 10024.110196000009, "eligible_miss": 83.0, "miss": 91.0, "model": 202.0, "overflow": 8.0, "padding": 378.0, "tokens": 35313.0 }, { "bucket": 3936.0, "duration_ms": 9968.116, "eligible_miss": 88.0, "miss": 90.0, "model": 213.0, "overflow": 2.0, "padding": 579.0, "tokens": 33164.0 }, { "bucket": 3808.0, "duration_ms": 9938.115310000003, "eligible_miss": 85.0, "miss": 91.0, "model": 210.0, "overflow": 6.0, "padding": 583.0, "tokens": 33657.0 }, { "bucket": 4000.0, "duration_ms": 10033.491619999997, "eligible_miss": 86.0, "miss": 91.0, "model": 216.0, "overflow": 5.0, "padding": 656.0, "tokens": 33781.0 }, { "bucket": 3552.0, "duration_ms": 9911.066888000005, "eligible_miss": 81.0, "miss": 90.0, "model": 201.0, "overflow": 9.0, "padding": 398.0, "tokens": 34386.0 }, { "bucket": 3744.0, "duration_ms": 10074.457772999996, "eligible_miss": 84.0, "miss": 91.0, "model": 208.0, "overflow": 7.0, "padding": 451.0, "tokens": 36056.0 }, { "bucket": 3712.0, "duration_ms": 9942.207149000005, "eligible_miss": 83.0, "miss": 90.0, "model": 206.0, "overflow": 7.0, "padding": 484.0, "tokens": 34082.0 }, { "bucket": 3712.0, "duration_ms": 9950.111710000001, "eligible_miss": 86.0, "miss": 91.0, "model": 207.0, "overflow": 5.0, "padding": 505.0, "tokens": 34159.0 }, { "bucket": 3904.0, "duration_ms": 10004.259407000001, "eligible_miss": 89.0, "miss": 91.0, "model": 213.0, "overflow": 2.0, "padding": 597.0, "tokens": 33971.0 }, { "bucket": 3744.0, "duration_ms": 9984.552112999998, "eligible_miss": 78.0, "miss": 90.0, "model": 207.0, "overflow": 12.0, "padding": 471.0, "tokens": 35554.0 }, { "bucket": 3424.0, "duration_ms": 9948.117576999995, "eligible_miss": 80.0, "miss": 91.0, "model": 198.0, "overflow": 11.0, "padding": 343.0, "tokens": 36906.0 }, { "bucket": 3584.0, "duration_ms": 10005.684332000004, "eligible_miss": 81.0, "miss": 91.0, "model": 203.0, "overflow": 10.0, "padding": 417.0, "tokens": 36166.0 }, { "bucket": 3680.0, "duration_ms": 9982.162338, "eligible_miss": 82.0, "miss": 90.0, "model": 205.0, "overflow": 8.0, "padding": 478.0, "tokens": 34720.0 }, { "bucket": 3648.0, "duration_ms": 9970.997752000007, "eligible_miss": 83.0, "miss": 91.0, "model": 205.0, "overflow": 8.0, "padding": 418.0, "tokens": 34115.0 }, { "bucket": 3648.0, "duration_ms": 10001.097707999996, "eligible_miss": 87.0, "miss": 91.0, "model": 205.0, "overflow": 4.0, "padding": 431.0, "tokens": 34821.0 }, { "bucket": 3648.0, "duration_ms": 9947.801385999994, "eligible_miss": 85.0, "miss": 90.0, "model": 204.0, "overflow": 5.0, "padding": 445.0, "tokens": 34615.0 }, { "bucket": 3712.0, "duration_ms": 10000.821746, "eligible_miss": 87.0, "miss": 91.0, "model": 207.0, "overflow": 4.0, "padding": 494.0, "tokens": 34429.0 }, { "bucket": 3712.0, "duration_ms": 10025.943433, "eligible_miss": 77.0, "miss": 91.0, "model": 207.0, "overflow": 14.0, "padding": 451.0, "tokens": 35074.0 }, { "bucket": 3648.0, "duration_ms": 9968.242391000002, "eligible_miss": 80.0, "miss": 90.0, "model": 204.0, "overflow": 10.0, "padding": 431.0, "tokens": 35314.0 }, { "bucket": 3808.0, "duration_ms": 9955.46471, "eligible_miss": 83.0, "miss": 91.0, "model": 210.0, "overflow": 8.0, "padding": 539.0, "tokens": 34463.0 }, { "bucket": 3776.0, "duration_ms": 10017.773912999995, "eligible_miss": 85.0, "miss": 91.0, "model": 209.0, "overflow": 6.0, "padding": 506.0, "tokens": 35333.0 }, { "bucket": 3712.0, "duration_ms": 9920.078849000001, "eligible_miss": 88.0, "miss": 90.0, "model": 206.0, "overflow": 2.0, "padding": 543.0, "tokens": 34287.0 }, { "bucket": 3616.0, "duration_ms": 10072.948714000007, "eligible_miss": 83.0, "miss": 91.0, "model": 204.0, "overflow": 8.0, "padding": 394.0, "tokens": 35149.0 }, { "bucket": 3392.0, "duration_ms": 9921.726875999999, "eligible_miss": 76.0, "miss": 90.0, "model": 196.0, "overflow": 14.0, "padding": 293.0, "tokens": 37023.0 }, { "bucket": 3808.0, "duration_ms": 9962.493520999991, "eligible_miss": 86.0, "miss": 91.0, "model": 210.0, "overflow": 5.0, "padding": 564.0, "tokens": 34152.0 }, { "bucket": 3840.0, "duration_ms": 10012.223253000006, "eligible_miss": 86.0, "miss": 91.0, "model": 211.0, "overflow": 5.0, "padding": 513.0, "tokens": 33611.0 }, { "bucket": 3808.0, "duration_ms": 9982.952109000005, "eligible_miss": 84.0, "miss": 90.0, "model": 209.0, "overflow": 6.0, "padding": 570.0, "tokens": 34152.0 }, { "bucket": 3744.0, "duration_ms": 9946.108181000001, "eligible_miss": 83.0, "miss": 91.0, "model": 208.0, "overflow": 8.0, "padding": 502.0, "tokens": 35237.0 }, { "bucket": 3744.0, "duration_ms": 10010.716567999994, "eligible_miss": 87.0, "miss": 91.0, "model": 208.0, "overflow": 4.0, "padding": 498.0, "tokens": 34119.0 }, { "bucket": 3648.0, "duration_ms": 10004.357205999999, "eligible_miss": 82.0, "miss": 90.0, "model": 204.0, "overflow": 8.0, "padding": 455.0, "tokens": 35705.0 }, { "bucket": 3456.0, "duration_ms": 9945.860283, "eligible_miss": 86.0, "miss": 91.0, "model": 199.0, "overflow": 5.0, "padding": 355.0, "tokens": 35520.0 }, { "bucket": 3872.0, "duration_ms": 10024.396264999998, "eligible_miss": 88.0, "miss": 91.0, "model": 212.0, "overflow": 3.0, "padding": 531.0, "tokens": 33351.0 }, { "bucket": 3872.0, "duration_ms": 9965.571466000003, "eligible_miss": 82.0, "miss": 90.0, "model": 211.0, "overflow": 8.0, "padding": 565.0, "tokens": 35270.0 }, { "bucket": 3872.0, "duration_ms": 9953.784156999998, "eligible_miss": 89.0, "miss": 91.0, "model": 212.0, "overflow": 2.0, "padding": 611.0, "tokens": 32037.0 }, { "bucket": 3488.0, "duration_ms": 10030.564947999997, "eligible_miss": 86.0, "miss": 91.0, "model": 200.0, "overflow": 5.0, "padding": 451.0, "tokens": 34202.0 }, { "bucket": 3680.0, "duration_ms": 9936.440215999995, "eligible_miss": 84.0, "miss": 90.0, "model": 205.0, "overflow": 6.0, "padding": 344.0, "tokens": 34514.0 } ], "clean": { "admitted": 4351, "completed": 4351, "completed_throughput_rps": 18.129166666666666, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 1387917, "offered_rps": 18.129166666666666, "output_tokens": 278464, "start_s": 60.0 }, "config": "C11", "drain_quarantined": false, "drain_seconds": 0.78110175699112, "latency_s": { "e2e": { "mean": 1.5956257307001827, "n": 4351, "p50": 1.5987792539817747, "p95": 1.7036471079918556, "p99": 1.7430243315029657 }, "tpot": { "mean": 0.024275665845246406, "n": 4351, "p50": 0.024345195381015185, "p95": 0.0258859295316229, "p99": 0.02641761801570528 }, "ttft": { "mean": 0.06625878244965909, "n": 4351, "p50": 0.06313588601187803, "p95": 0.10306648399273399, "p99": 0.10799207250238396 } }, "layer1": { "decode_tokens": 274144, "kv_usage_max": 0.04047490555855371, "kv_usage_mean": 0.03138338971244831, "mode_counts": { "FULL": 5554, "NONE": 4351 }, "mode_shares": { "FULL": 0.5607269056032307, "NONE": 0.4392730943967693 }, "preemptions": 0, "prefill_tokens": 1387663, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 0, "queue_waiting_mean": 0.0, "records_all": 14187, "records_clean": 9905, "requests_per_step": { "mean": 28.11660777385159, "n": 9905, "p50": 28.0, "p95": 30.0, "p99": 31.0 }, "scheduled_tokens_per_step": { "mean": 167.77455830388692, "n": 9905, "p50": 29.0, "p95": 498.0, "p99": 531.0 }, "step_duration_ms": { "mean": 48.36846449651691, "n": 9905, "p50": 53.217559, "p95": 64.57586499999995, "p99": 87.24098867999997 }, "token_efficiency_per_ms": 3.4686765447344032 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P01", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 18.05, "clean_c_waiting_median": 0.0, "completion_rate_rps": 26.6, "completion_rate_within_10pct": false, "tail_end_s": 347.03789717299514, "tail_start_s": 337.03789717299514, "valid": false, "waiting_median": 13.0, "waiting_within_10pct": false, "window": 1 }, { "clean_c_completion_rate_median_rps": 18.05, "clean_c_waiting_median": 0.0, "completion_rate_rps": 27.4, "completion_rate_within_10pct": false, "tail_end_s": 394.36406223100494, "tail_start_s": 384.36406223100494, "valid": false, "waiting_median": 25.0, "waiting_within_10pct": false, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 4351, "run_dir": "runs/phase3/primary/P01-C11/moderate", "run_id": "P01-C11-moderate", "trace_files": 2, "waste": { "R128": 0.3723323346172142, "R32": 0.3612776759520059, "R64": 0.36868249852408347, "bucket_slack": 0.031357776531205854, "eligible_miss_rate": 0.406663301362948, "graph_miss_rate": 0.4392730943967693, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 4351, "moe_layer_cv": null, "overflow_rate": 0.032609793033821305, "padded_tokens_per_useful_token": 0.013762127611690166, "padding_fraction": 0.12867978033849478 } }, "P01-C11-saturation": { "blocks": [ { "bucket": 6400.0, "duration_ms": 9854.135549999999, "eligible_miss": 2.0, "miss": 37.0, "model": 137.0, "overflow": 35.0, "padding": 2.0, "tokens": 59578.0 }, { "bucket": 7552.0, "duration_ms": 9896.006353999996, "eligible_miss": 2.0, "miss": 34.0, "model": 152.0, "overflow": 32.0, "padding": 2.0, "tokens": 56340.0 }, { "bucket": 8448.0, "duration_ms": 10198.840811000002, "eligible_miss": 1.0, "miss": 35.0, "model": 167.0, "overflow": 34.0, "padding": 3.0, "tokens": 55828.0 }, { "bucket": 6400.0, "duration_ms": 9857.422299999998, "eligible_miss": 2.0, "miss": 39.0, "model": 139.0, "overflow": 37.0, "padding": 2.0, "tokens": 60921.0 }, { "bucket": 8896.0, "duration_ms": 9893.559951000003, "eligible_miss": 2.0, "miss": 31.0, "model": 170.0, "overflow": 29.0, "padding": 2.0, "tokens": 52396.0 }, { "bucket": 7104.0, "duration_ms": 10051.639851999997, "eligible_miss": 3.0, "miss": 38.0, "model": 149.0, "overflow": 35.0, "padding": 3.0, "tokens": 59830.0 }, { "bucket": 6784.0, "duration_ms": 9926.596741999998, "eligible_miss": 1.0, "miss": 37.0, "model": 143.0, "overflow": 36.0, "padding": 2.0, "tokens": 59476.0 }, { "bucket": 9216.0, "duration_ms": 10039.259791, "eligible_miss": 3.0, "miss": 32.0, "model": 176.0, "overflow": 29.0, "padding": 3.0, "tokens": 53246.0 }, { "bucket": 6400.0, "duration_ms": 10069.991445000001, "eligible_miss": 1.0, "miss": 38.0, "model": 138.0, "overflow": 37.0, "padding": 2.0, "tokens": 63144.0 }, { "bucket": 7104.0, "duration_ms": 9825.774603999995, "eligible_miss": 2.0, "miss": 35.0, "model": 146.0, "overflow": 33.0, "padding": 2.0, "tokens": 58761.0 }, { "bucket": 8896.0, "duration_ms": 10039.997257, "eligible_miss": 3.0, "miss": 32.0, "model": 171.0, "overflow": 29.0, "padding": 3.0, "tokens": 53282.0 }, { "bucket": 6336.0, "duration_ms": 10105.074265000001, "eligible_miss": 3.0, "miss": 40.0, "model": 139.0, "overflow": 37.0, "padding": 2.0, "tokens": 62032.0 }, { "bucket": 7168.0, "duration_ms": 9824.336723000004, "eligible_miss": 4.0, "miss": 37.0, "model": 149.0, "overflow": 33.0, "padding": 2.0, "tokens": 56409.0 }, { "bucket": 8512.0, "duration_ms": 10174.319685999995, "eligible_miss": 5.0, "miss": 36.0, "model": 169.0, "overflow": 31.0, "padding": 3.0, "tokens": 56319.0 }, { "bucket": 6272.0, "duration_ms": 9881.112864000002, "eligible_miss": 4.0, "miss": 40.0, "model": 138.0, "overflow": 36.0, "padding": 2.0, "tokens": 60881.0 }, { "bucket": 7872.0, "duration_ms": 9879.054422000001, "eligible_miss": 3.0, "miss": 36.0, "model": 159.0, "overflow": 33.0, "padding": 2.0, "tokens": 55569.0 }, { "bucket": 7808.0, "duration_ms": 10085.14763200001, "eligible_miss": 4.0, "miss": 36.0, "model": 158.0, "overflow": 32.0, "padding": 3.0, "tokens": 57772.0 }, { "bucket": 6272.0, "duration_ms": 10021.492237000002, "eligible_miss": 2.0, "miss": 42.0, "model": 140.0, "overflow": 40.0, "padding": 2.0, "tokens": 62027.0 }, { "bucket": 8320.0, "duration_ms": 9862.347805999994, "eligible_miss": 5.0, "miss": 34.0, "model": 164.0, "overflow": 29.0, "padding": 2.0, "tokens": 53646.0 }, { "bucket": 7360.0, "duration_ms": 10213.140882999996, "eligible_miss": 4.0, "miss": 40.0, "model": 155.0, "overflow": 36.0, "padding": 3.0, "tokens": 59510.0 }, { "bucket": 6272.0, "duration_ms": 9961.871976000002, "eligible_miss": 1.0, "miss": 39.0, "model": 137.0, "overflow": 38.0, "padding": 2.0, "tokens": 61272.0 }, { "bucket": 8768.0, "duration_ms": 9788.361232000007, "eligible_miss": 2.0, "miss": 33.0, "model": 170.0, "overflow": 31.0, "padding": 2.0, "tokens": 50522.0 }, { "bucket": 6912.0, "duration_ms": 10077.373054000002, "eligible_miss": 3.0, "miss": 41.0, "model": 149.0, "overflow": 38.0, "padding": 3.0, "tokens": 59342.0 }, { "bucket": 6656.0, "duration_ms": 9893.422728000001, "eligible_miss": 2.0, "miss": 39.0, "model": 143.0, "overflow": 37.0, "padding": 2.0, "tokens": 58372.0 }, { "bucket": 8896.0, "duration_ms": 9963.152674999996, "eligible_miss": 2.0, "miss": 32.0, "model": 171.0, "overflow": 30.0, "padding": 2.0, "tokens": 51851.0 }, { "bucket": 6400.0, "duration_ms": 10128.076877, "eligible_miss": 2.0, "miss": 41.0, "model": 141.0, "overflow": 39.0, "padding": 3.0, "tokens": 63078.0 }, { "bucket": 6720.0, "duration_ms": 9840.454017, "eligible_miss": 3.0, "miss": 39.0, "model": 144.0, "overflow": 36.0, "padding": 2.0, "tokens": 56898.0 }, { "bucket": 8960.0, "duration_ms": 10069.613022000003, "eligible_miss": 3.0, "miss": 33.0, "model": 173.0, "overflow": 30.0, "padding": 3.0, "tokens": 52424.0 }, { "bucket": 6272.0, "duration_ms": 10086.144182999995, "eligible_miss": 2.0, "miss": 41.0, "model": 139.0, "overflow": 39.0, "padding": 2.0, "tokens": 63091.0 }, { "bucket": 7616.0, "duration_ms": 9819.59047, "eligible_miss": 3.0, "miss": 38.0, "model": 157.0, "overflow": 35.0, "padding": 2.0, "tokens": 54925.0 }, { "bucket": 8064.0, "duration_ms": 10084.262563999993, "eligible_miss": 4.0, "miss": 38.0, "model": 164.0, "overflow": 34.0, "padding": 3.0, "tokens": 56586.0 }, { "bucket": 6272.0, "duration_ms": 9973.057058000002, "eligible_miss": 3.0, "miss": 40.0, "model": 138.0, "overflow": 37.0, "padding": 2.0, "tokens": 62642.0 }, { "bucket": 8576.0, "duration_ms": 9906.256273999996, "eligible_miss": 3.0, "miss": 34.0, "model": 168.0, "overflow": 31.0, "padding": 2.0, "tokens": 52036.0 }, { "bucket": 7104.0, "duration_ms": 10073.656216999998, "eligible_miss": 3.0, "miss": 40.0, "model": 151.0, "overflow": 37.0, "padding": 3.0, "tokens": 59041.0 }, { "bucket": 6784.0, "duration_ms": 9879.548074999997, "eligible_miss": 2.0, "miss": 40.0, "model": 146.0, "overflow": 38.0, "padding": 2.0, "tokens": 57531.0 }, { "bucket": 8896.0, "duration_ms": 10182.290707999993, "eligible_miss": 4.0, "miss": 35.0, "model": 174.0, "overflow": 31.0, "padding": 3.0, "tokens": 54155.0 }, { "bucket": 6272.0, "duration_ms": 9961.884863999998, "eligible_miss": 2.0, "miss": 40.0, "model": 138.0, "overflow": 38.0, "padding": 2.0, "tokens": 62473.0 }, { "bucket": 6912.0, "duration_ms": 9816.541234000002, "eligible_miss": 2.0, "miss": 37.0, "model": 145.0, "overflow": 35.0, "padding": 2.0, "tokens": 57702.0 }, { "bucket": 8768.0, "duration_ms": 10041.103434999999, "eligible_miss": 3.0, "miss": 34.0, "model": 171.0, "overflow": 31.0, "padding": 3.0, "tokens": 53200.0 }, { "bucket": 6272.0, "duration_ms": 10059.006235000004, "eligible_miss": 2.0, "miss": 41.0, "model": 139.0, "overflow": 39.0, "padding": 2.0, "tokens": 61771.0 }, { "bucket": 7872.0, "duration_ms": 9881.051967000003, "eligible_miss": 2.0, "miss": 37.0, "model": 160.0, "overflow": 35.0, "padding": 2.0, "tokens": 54044.0 }, { "bucket": 7808.0, "duration_ms": 10117.143586, "eligible_miss": 3.0, "miss": 39.0, "model": 161.0, "overflow": 36.0, "padding": 3.0, "tokens": 58050.0 }, { "bucket": 6272.0, "duration_ms": 9970.732670000003, "eligible_miss": 2.0, "miss": 41.0, "model": 139.0, "overflow": 39.0, "padding": 2.0, "tokens": 60989.0 }, { "bucket": 8640.0, "duration_ms": 9859.881477999996, "eligible_miss": 2.0, "miss": 32.0, "model": 167.0, "overflow": 30.0, "padding": 2.0, "tokens": 52243.0 }, { "bucket": 7040.0, "duration_ms": 10080.299878999997, "eligible_miss": 3.0, "miss": 40.0, "model": 150.0, "overflow": 37.0, "padding": 3.0, "tokens": 59585.0 }, { "bucket": 6336.0, "duration_ms": 10006.960603000003, "eligible_miss": 2.0, "miss": 40.0, "model": 139.0, "overflow": 38.0, "padding": 2.0, "tokens": 60367.0 }, { "bucket": 9280.0, "duration_ms": 9888.519409999994, "eligible_miss": 2.0, "miss": 32.0, "model": 177.0, "overflow": 30.0, "padding": 2.0, "tokens": 51283.0 }, { "bucket": 6336.0, "duration_ms": 10039.603299999999, "eligible_miss": 2.0, "miss": 41.0, "model": 140.0, "overflow": 39.0, "padding": 3.0, "tokens": 60761.0 } ], "clean": { "admitted": 7252, "completed": 7252, "completed_throughput_rps": 30.216666666666665, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 2308997, "offered_rps": 30.216666666666665, "output_tokens": 464128, "start_s": 60.0 }, "config": "C11", "drain_quarantined": false, "drain_seconds": 7.466667815984692, "latency_s": { "e2e": { "mean": 8.479005430775388, "n": 7252, "p50": 8.488157999003306, "p95": 8.62182870524848, "p99": 8.659005985551339 }, "tpot": { "mean": 0.030981617798706566, "n": 7252, "p50": 0.03097177065062588, "p95": 0.032257703036515206, "p99": 0.032861725646782566 }, "ttft": { "mean": 6.527163509456874, "n": 7252, "p50": 6.528871715505375, "p95": 6.666822149860673, "p99": 6.698687153424544 } }, "layer1": { "decode_tokens": 455861, "kv_usage_max": 0.08202914193200217, "kv_usage_mean": 0.07020805987115446, "mode_counts": { "FULL": 5564, "NONE": 1786 }, "mode_shares": { "FULL": 0.7570068027210884, "NONE": 0.24299319727891155 }, "preemptions": 0, "prefill_tokens": 2307340, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 192, "queue_waiting_mean": 191.0134693877551, "records_all": 11380, "records_clean": 7350, "requests_per_step": { "mean": 63.01319727891156, "n": 7350, "p50": 64.0, "p95": 64.0, "p99": 64.0 }, "scheduled_tokens_per_step": { "mean": 375.9457142857143, "n": 7350, "p50": 64.0, "p95": 1647.5499999999993, "p99": 1965.5100000000002 }, "step_duration_ms": { "mean": 65.19035523346939, "n": 7350, "p50": 33.147161, "p95": 185.55763439999998, "p99": 202.8066175900001 }, "token_efficiency_per_ms": 5.766891635109544 }, "layer2_missing_after_controller_cleanup": false, "load": "saturation", "pattern": "P01", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 29.9, "clean_c_waiting_median": 192.0, "completion_rate_rps": 31.6, "completion_rate_within_10pct": true, "tail_end_s": 342.5308606699982, "tail_start_s": 332.5308606699982, "valid": true, "waiting_median": 192.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 29.9, "clean_c_waiting_median": 192.0, "completion_rate_rps": 28.9, "completion_rate_within_10pct": true, "tail_end_s": 375.9222603540111, "tail_start_s": 365.9222603540111, "valid": true, "waiting_median": 192.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": true, "requests_completed": 7252, "run_dir": "runs/phase3/primary/P01-C11/saturation", "run_id": "P01-C11-saturation", "trace_files": 2, "waste": { "R128": 0.3723323346172142, "R32": 0.3612776759520059, "R64": 0.36868249852408347, "bucket_slack": 0.0024497562729742686, "eligible_miss_rate": 0.017006802721088437, "graph_miss_rate": 0.24299319727891155, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.22598639455782313, "padded_tokens_per_useful_token": 4.089460013947592e-05, "padding_fraction": 0.0003173301581595974 } }, "P02-C00-moderate": { "blocks": [ { "bucket": 24032.0, "duration_ms": 9990.374930999998, "eligible_miss": 0.0, "miss": 4.0, "model": 191.0, "overflow": 4.0, "padding": 430.0, "tokens": 25800.0 }, { "bucket": 21776.0, "duration_ms": 9970.567963999998, "eligible_miss": 0.0, "miss": 11.0, "model": 186.0, "overflow": 11.0, "padding": 334.0, "tokens": 27607.0 }, { "bucket": 25304.0, "duration_ms": 9978.748167999998, "eligible_miss": 0.0, "miss": 4.0, "model": 193.0, "overflow": 4.0, "padding": 430.0, "tokens": 27110.0 }, { "bucket": 24360.0, "duration_ms": 9948.932990000003, "eligible_miss": 0.0, "miss": 5.0, "model": 191.0, "overflow": 5.0, "padding": 501.0, "tokens": 26593.0 }, { "bucket": 23512.0, "duration_ms": 10021.978742000003, "eligible_miss": 0.0, "miss": 6.0, "model": 192.0, "overflow": 6.0, "padding": 547.0, "tokens": 26380.0 }, { "bucket": 22864.0, "duration_ms": 9986.585967999992, "eligible_miss": 0.0, "miss": 9.0, "model": 187.0, "overflow": 9.0, "padding": 455.0, "tokens": 27383.0 }, { "bucket": 23008.0, "duration_ms": 9962.632415999997, "eligible_miss": 0.0, "miss": 8.0, "model": 190.0, "overflow": 8.0, "padding": 481.0, "tokens": 26882.0 }, { "bucket": 20856.0, "duration_ms": 9993.166222000002, "eligible_miss": 0.0, "miss": 12.0, "model": 191.0, "overflow": 12.0, "padding": 386.0, "tokens": 27222.0 }, { "bucket": 23232.0, "duration_ms": 9980.531696, "eligible_miss": 0.0, "miss": 5.0, "model": 190.0, "overflow": 5.0, "padding": 484.0, "tokens": 25604.0 }, { "bucket": 23568.0, "duration_ms": 9962.036962000002, "eligible_miss": 0.0, "miss": 5.0, "model": 187.0, "overflow": 5.0, "padding": 441.0, "tokens": 25962.0 }, { "bucket": 23928.0, "duration_ms": 10001.557425999998, "eligible_miss": 0.0, "miss": 4.0, "model": 189.0, "overflow": 4.0, "padding": 382.0, "tokens": 25751.0 }, { "bucket": 22448.0, "duration_ms": 9945.918971, "eligible_miss": 0.0, "miss": 9.0, "model": 187.0, "overflow": 9.0, "padding": 259.0, "tokens": 27301.0 }, { "bucket": 21776.0, "duration_ms": 10029.021144000002, "eligible_miss": 0.0, "miss": 10.0, "model": 192.0, "overflow": 10.0, "padding": 400.0, "tokens": 26851.0 }, { "bucket": 22024.0, "duration_ms": 9953.179873999998, "eligible_miss": 0.0, "miss": 9.0, "model": 190.0, "overflow": 9.0, "padding": 389.0, "tokens": 26662.0 }, { "bucket": 23864.0, "duration_ms": 9947.728225000004, "eligible_miss": 0.0, "miss": 6.0, "model": 188.0, "overflow": 6.0, "padding": 457.0, "tokens": 26707.0 }, { "bucket": 22440.0, "duration_ms": 10006.012027999996, "eligible_miss": 0.0, "miss": 10.0, "model": 189.0, "overflow": 10.0, "padding": 464.0, "tokens": 27499.0 }, { "bucket": 23464.0, "duration_ms": 9976.957411999996, "eligible_miss": 0.0, "miss": 7.0, "model": 189.0, "overflow": 7.0, "padding": 373.0, "tokens": 27006.0 }, { "bucket": 21184.0, "duration_ms": 9958.724134999997, "eligible_miss": 0.0, "miss": 12.0, "model": 189.0, "overflow": 12.0, "padding": 304.0, "tokens": 27389.0 }, { "bucket": 23560.0, "duration_ms": 9988.031766000007, "eligible_miss": 0.0, "miss": 5.0, "model": 191.0, "overflow": 5.0, "padding": 460.0, "tokens": 25824.0 }, { "bucket": 23512.0, "duration_ms": 10011.898985999998, "eligible_miss": 0.0, "miss": 8.0, "model": 187.0, "overflow": 8.0, "padding": 434.0, "tokens": 27497.0 }, { "bucket": 23656.0, "duration_ms": 9966.358194999993, "eligible_miss": 0.0, "miss": 6.0, "model": 190.0, "overflow": 6.0, "padding": 455.0, "tokens": 26595.0 }, { "bucket": 22424.0, "duration_ms": 10001.583119000004, "eligible_miss": 0.0, "miss": 9.0, "model": 192.0, "overflow": 9.0, "padding": 395.0, "tokens": 27027.0 }, { "bucket": 22496.0, "duration_ms": 9992.83060800001, "eligible_miss": 0.0, "miss": 7.0, "model": 194.0, "overflow": 7.0, "padding": 558.0, "tokens": 25824.0 }, { "bucket": 23264.0, "duration_ms": 9970.569579999998, "eligible_miss": 0.0, "miss": 6.0, "model": 195.0, "overflow": 6.0, "padding": 710.0, "tokens": 25915.0 }, { "bucket": 21720.0, "duration_ms": 9988.029574999997, "eligible_miss": 0.0, "miss": 10.0, "model": 189.0, "overflow": 10.0, "padding": 639.0, "tokens": 26748.0 }, { "bucket": 23936.0, "duration_ms": 9961.957320999996, "eligible_miss": 0.0, "miss": 6.0, "model": 190.0, "overflow": 6.0, "padding": 614.0, "tokens": 26614.0 }, { "bucket": 23280.0, "duration_ms": 9992.756356000002, "eligible_miss": 0.0, "miss": 7.0, "model": 191.0, "overflow": 7.0, "padding": 489.0, "tokens": 26596.0 }, { "bucket": 23384.0, "duration_ms": 9956.727936000005, "eligible_miss": 0.0, "miss": 8.0, "model": 190.0, "overflow": 8.0, "padding": 487.0, "tokens": 27340.0 }, { "bucket": 21592.0, "duration_ms": 10004.012218000007, "eligible_miss": 0.0, "miss": 11.0, "model": 191.0, "overflow": 11.0, "padding": 507.0, "tokens": 27266.0 }, { "bucket": 22712.0, "duration_ms": 9969.233649999993, "eligible_miss": 0.0, "miss": 7.0, "model": 189.0, "overflow": 7.0, "padding": 507.0, "tokens": 26147.0 }, { "bucket": 23144.0, "duration_ms": 9995.538473, "eligible_miss": 0.0, "miss": 4.0, "model": 193.0, "overflow": 4.0, "padding": 503.0, "tokens": 24863.0 }, { "bucket": 23232.0, "duration_ms": 9948.029670000002, "eligible_miss": 0.0, "miss": 6.0, "model": 189.0, "overflow": 6.0, "padding": 538.0, "tokens": 26057.0 }, { "bucket": 23512.0, "duration_ms": 9983.782809999999, "eligible_miss": 0.0, "miss": 6.0, "model": 191.0, "overflow": 6.0, "padding": 528.0, "tokens": 26292.0 }, { "bucket": 22096.0, "duration_ms": 9981.637089999998, "eligible_miss": 0.0, "miss": 10.0, "model": 189.0, "overflow": 10.0, "padding": 490.0, "tokens": 27165.0 }, { "bucket": 23016.0, "duration_ms": 9990.229410999998, "eligible_miss": 0.0, "miss": 7.0, "model": 192.0, "overflow": 7.0, "padding": 458.0, "tokens": 26417.0 }, { "bucket": 23520.0, "duration_ms": 9964.634507999997, "eligible_miss": 0.0, "miss": 7.0, "model": 190.0, "overflow": 7.0, "padding": 496.0, "tokens": 27013.0 }, { "bucket": 22984.0, "duration_ms": 9985.033693000001, "eligible_miss": 0.0, "miss": 7.0, "model": 191.0, "overflow": 7.0, "padding": 561.0, "tokens": 26179.0 }, { "bucket": 23072.0, "duration_ms": 10000.245900999998, "eligible_miss": 0.0, "miss": 6.0, "model": 189.0, "overflow": 6.0, "padding": 485.0, "tokens": 25902.0 }, { "bucket": 23200.0, "duration_ms": 9981.013887000003, "eligible_miss": 0.0, "miss": 7.0, "model": 188.0, "overflow": 7.0, "padding": 430.0, "tokens": 26600.0 }, { "bucket": 21640.0, "duration_ms": 9972.11258, "eligible_miss": 0.0, "miss": 10.0, "model": 190.0, "overflow": 10.0, "padding": 369.0, "tokens": 26891.0 }, { "bucket": 24960.0, "duration_ms": 10021.411613000006, "eligible_miss": 0.0, "miss": 6.0, "model": 186.0, "overflow": 6.0, "padding": 432.0, "tokens": 27757.0 }, { "bucket": 24344.0, "duration_ms": 9947.654753000003, "eligible_miss": 0.0, "miss": 4.0, "model": 191.0, "overflow": 4.0, "padding": 377.0, "tokens": 26135.0 }, { "bucket": 23384.0, "duration_ms": 9983.115876, "eligible_miss": 0.0, "miss": 6.0, "model": 191.0, "overflow": 6.0, "padding": 327.0, "tokens": 26392.0 }, { "bucket": 23560.0, "duration_ms": 9962.658046, "eligible_miss": 0.0, "miss": 6.0, "model": 191.0, "overflow": 6.0, "padding": 489.0, "tokens": 26471.0 }, { "bucket": 22432.0, "duration_ms": 9994.31181, "eligible_miss": 0.0, "miss": 9.0, "model": 188.0, "overflow": 9.0, "padding": 458.0, "tokens": 27072.0 }, { "bucket": 22200.0, "duration_ms": 9995.201477000002, "eligible_miss": 0.0, "miss": 7.0, "model": 191.0, "overflow": 7.0, "padding": 446.0, "tokens": 25703.0 }, { "bucket": 21776.0, "duration_ms": 9962.024166000001, "eligible_miss": 0.0, "miss": 10.0, "model": 190.0, "overflow": 10.0, "padding": 390.0, "tokens": 26955.0 }, { "bucket": 23576.0, "duration_ms": 9965.013077000003, "eligible_miss": 0.0, "miss": 6.0, "model": 192.0, "overflow": 6.0, "padding": 523.0, "tokens": 26357.0 } ], "clean": { "admitted": 1536, "completed": 1537, "completed_throughput_rps": 6.404166666666667, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 493355, "offered_rps": 6.4, "output_tokens": 786944, "start_s": 60.0 }, "config": "C00", "drain_quarantined": false, "drain_seconds": 8.726939176005544, "latency_s": { "e2e": { "mean": 13.527924079167455, "n": 1537, "p50": 13.537170164985582, "p95": 13.641508429596433, "p99": 13.721163101642158 }, "tpot": { "mean": 0.026301412165737215, "n": 1537, "p50": 0.026317087653602897, "p95": 0.026532306089241387, "p99": 0.02667916153010606 }, "ttft": { "mean": 0.08790246247573787, "n": 1537, "p50": 0.08802004699828103, "p95": 0.10394775940803809, "p99": 0.1072390887804795 } }, "layer1": { "decode_tokens": 785211, "kv_usage_max": 0.1826439578264396, "kv_usage_mean": 0.17062570582816017, "mode_counts": { "FULL": 7586, "NONE": 350, "PIECEWISE": 1186 }, "mode_shares": { "FULL": 0.8316158737119053, "NONE": 0.03836877877658408, "PIECEWISE": 0.13001534751151064 }, "preemptions": 0, "prefill_tokens": 492112, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 0, "queue_waiting_mean": 0.0, "records_all": 14298, "records_clean": 9122, "requests_per_step": { "mean": 86.24720456040342, "n": 9122, "p50": 86.0, "p95": 87.0, "p99": 88.0 }, "scheduled_tokens_per_step": { "mean": 140.02663889497916, "n": 9122, "p50": 86.0, "p95": 487.9499999999989, "p99": 575.0 }, "step_duration_ms": { "mean": 52.51614705382592, "n": 9122, "p50": 45.163168, "p95": 74.58838244999998, "p99": 78.05190758999998 }, "token_efficiency_per_ms": 2.6663540025405945 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P02", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 6.4, "clean_c_waiting_median": 0.0, "completion_rate_rps": 6.8, "completion_rate_within_10pct": true, "tail_end_s": 333.57828441497986, "tail_start_s": 323.57828441497986, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 6.4, "clean_c_waiting_median": 0.0, "completion_rate_rps": 7.0, "completion_rate_within_10pct": true, "tail_end_s": 367.5501277539879, "tail_start_s": 357.5501277539879, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": true, "requests_completed": 1537, "run_dir": "runs/phase3/primary/P02-C00/moderate", "run_id": "P02-C00-moderate", "trace_files": 2, "waste": { "R128": 0.3723323346172142, "R32": 0.3612776759520059, "R64": 0.36868249852408347, "bucket_slack": 0.019977842624707646, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.03836877877658408, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 1536, "moe_layer_cv": null, "overflow_rate": 0.03836877877658408, "padded_tokens_per_useful_token": 0.017279889268415272, "padding_fraction": 0.019977842624707646 } }, "P02-C00-saturation": { "blocks": [ { "bucket": 31744.0, "duration_ms": 10002.675380000002, "eligible_miss": 0.0, "miss": 0.0, "model": 124.0, "overflow": 0.0, "padding": 0.0, "tokens": 31744.0 }, { "bucket": 30464.0, "duration_ms": 9977.405133999999, "eligible_miss": 0.0, "miss": 0.0, "model": 119.0, "overflow": 0.0, "padding": 0.0, "tokens": 30464.0 }, { "bucket": 10616.0, "duration_ms": 10968.631501000002, "eligible_miss": 0.0, "miss": 10.0, "model": 51.0, "overflow": 10.0, "padding": 13.0, "tokens": 91371.0 }, { "bucket": 28928.0, "duration_ms": 9062.709024, "eligible_miss": 0.0, "miss": 1.0, "model": 114.0, "overflow": 1.0, "padding": 0.0, "tokens": 34646.0 }, { "bucket": 32768.0, "duration_ms": 9948.836104999998, "eligible_miss": 0.0, "miss": 0.0, "model": 128.0, "overflow": 0.0, "padding": 0.0, "tokens": 32768.0 }, { "bucket": 31232.0, "duration_ms": 9969.489221000005, "eligible_miss": 0.0, "miss": 0.0, "model": 122.0, "overflow": 0.0, "padding": 0.0, "tokens": 31232.0 }, { "bucket": 30208.0, "duration_ms": 9988.825041999999, "eligible_miss": 0.0, "miss": 0.0, "model": 118.0, "overflow": 0.0, "padding": 0.0, "tokens": 30208.0 }, { "bucket": 5616.0, "duration_ms": 10101.62816, "eligible_miss": 0.0, "miss": 12.0, "model": 34.0, "overflow": 12.0, "padding": 8.0, "tokens": 89499.0 }, { "bucket": 35072.0, "duration_ms": 9878.621836, "eligible_miss": 0.0, "miss": 0.0, "model": 137.0, "overflow": 0.0, "padding": 0.0, "tokens": 35072.0 }, { "bucket": 33024.0, "duration_ms": 10043.882824999999, "eligible_miss": 0.0, "miss": 0.0, "model": 129.0, "overflow": 0.0, "padding": 0.0, "tokens": 33024.0 }, { "bucket": 31488.0, "duration_ms": 9993.030219000004, "eligible_miss": 0.0, "miss": 0.0, "model": 123.0, "overflow": 0.0, "padding": 0.0, "tokens": 31488.0 }, { "bucket": 29072.0, "duration_ms": 10687.022778, "eligible_miss": 0.0, "miss": 2.0, "model": 115.0, "overflow": 2.0, "padding": 16.0, "tokens": 44531.0 }, { "bucket": 9472.0, "duration_ms": 9269.511275, "eligible_miss": 0.0, "miss": 9.0, "model": 46.0, "overflow": 9.0, "padding": 0.0, "tokens": 76327.0 }, { "bucket": 34304.0, "duration_ms": 9932.089161000004, "eligible_miss": 0.0, "miss": 0.0, "model": 134.0, "overflow": 0.0, "padding": 0.0, "tokens": 34304.0 }, { "bucket": 32768.0, "duration_ms": 10036.932253, "eligible_miss": 0.0, "miss": 0.0, "model": 128.0, "overflow": 0.0, "padding": 0.0, "tokens": 32768.0 }, { "bucket": 30976.0, "duration_ms": 9951.556923999999, "eligible_miss": 0.0, "miss": 0.0, "model": 121.0, "overflow": 0.0, "padding": 0.0, "tokens": 30976.0 }, { "bucket": 21408.0, "duration_ms": 10437.419686000003, "eligible_miss": 0.0, "miss": 5.0, "model": 88.0, "overflow": 5.0, "padding": 21.0, "tokens": 59530.0 }, { "bucket": 18176.0, "duration_ms": 9570.746277, "eligible_miss": 0.0, "miss": 6.0, "model": 77.0, "overflow": 6.0, "padding": 0.0, "tokens": 63405.0 }, { "bucket": 34048.0, "duration_ms": 9934.429371999997, "eligible_miss": 0.0, "miss": 0.0, "model": 133.0, "overflow": 0.0, "padding": 0.0, "tokens": 34048.0 }, { "bucket": 32512.0, "duration_ms": 10015.332801000004, "eligible_miss": 0.0, "miss": 0.0, "model": 127.0, "overflow": 0.0, "padding": 0.0, "tokens": 32512.0 }, { "bucket": 30976.0, "duration_ms": 9991.365666000003, "eligible_miss": 0.0, "miss": 0.0, "model": 121.0, "overflow": 0.0, "padding": 0.0, "tokens": 30976.0 }, { "bucket": 12784.0, "duration_ms": 10683.046393999997, "eligible_miss": 0.0, "miss": 10.0, "model": 60.0, "overflow": 10.0, "padding": 8.0, "tokens": 82291.0 }, { "bucket": 27136.0, "duration_ms": 9277.709315999997, "eligible_miss": 0.0, "miss": 2.0, "model": 108.0, "overflow": 2.0, "padding": 0.0, "tokens": 42721.0 }, { "bucket": 33792.0, "duration_ms": 9982.370690000003, "eligible_miss": 0.0, "miss": 0.0, "model": 132.0, "overflow": 0.0, "padding": 0.0, "tokens": 33792.0 }, { "bucket": 32000.0, "duration_ms": 10015.234685000001, "eligible_miss": 0.0, "miss": 0.0, "model": 125.0, "overflow": 0.0, "padding": 0.0, "tokens": 32000.0 }, { "bucket": 30464.0, "duration_ms": 9969.169197999998, "eligible_miss": 0.0, "miss": 0.0, "model": 119.0, "overflow": 0.0, "padding": 0.0, "tokens": 30464.0 }, { "bucket": 6592.0, "duration_ms": 9960.992191000003, "eligible_miss": 0.0, "miss": 11.0, "model": 36.0, "overflow": 11.0, "padding": 17.0, "tokens": 88758.0 }, { "bucket": 35840.0, "duration_ms": 10018.960007, "eligible_miss": 0.0, "miss": 0.0, "model": 140.0, "overflow": 0.0, "padding": 0.0, "tokens": 35840.0 }, { "bucket": 33280.0, "duration_ms": 10004.701410999998, "eligible_miss": 0.0, "miss": 0.0, "model": 130.0, "overflow": 0.0, "padding": 0.0, "tokens": 33280.0 }, { "bucket": 31744.0, "duration_ms": 9991.484610999996, "eligible_miss": 0.0, "miss": 0.0, "model": 124.0, "overflow": 0.0, "padding": 0.0, "tokens": 31744.0 }, { "bucket": 26976.0, "duration_ms": 10646.21925, "eligible_miss": 0.0, "miss": 3.0, "model": 108.0, "overflow": 3.0, "padding": 23.0, "tokens": 48965.0 }, { "bucket": 11776.0, "duration_ms": 9300.176934000001, "eligible_miss": 0.0, "miss": 9.0, "model": 55.0, "overflow": 9.0, "padding": 0.0, "tokens": 71947.0 }, { "bucket": 34560.0, "duration_ms": 9969.634924, "eligible_miss": 0.0, "miss": 0.0, "model": 135.0, "overflow": 0.0, "padding": 0.0, "tokens": 34560.0 }, { "bucket": 32768.0, "duration_ms": 10059.361980999998, "eligible_miss": 0.0, "miss": 0.0, "model": 128.0, "overflow": 0.0, "padding": 0.0, "tokens": 32768.0 }, { "bucket": 30976.0, "duration_ms": 9932.953102000003, "eligible_miss": 0.0, "miss": 0.0, "model": 121.0, "overflow": 0.0, "padding": 0.0, "tokens": 30976.0 }, { "bucket": 18544.0, "duration_ms": 10893.108333, "eligible_miss": 0.0, "miss": 7.0, "model": 79.0, "overflow": 7.0, "padding": 21.0, "tokens": 71776.0 }, { "bucket": 20992.0, "duration_ms": 9086.406721000005, "eligible_miss": 0.0, "miss": 5.0, "model": 87.0, "overflow": 5.0, "padding": 0.0, "tokens": 51818.0 }, { "bucket": 33536.0, "duration_ms": 9975.697529000003, "eligible_miss": 0.0, "miss": 0.0, "model": 131.0, "overflow": 0.0, "padding": 0.0, "tokens": 33536.0 }, { "bucket": 31744.0, "duration_ms": 9990.059341000002, "eligible_miss": 0.0, "miss": 0.0, "model": 124.0, "overflow": 0.0, "padding": 0.0, "tokens": 31744.0 }, { "bucket": 30464.0, "duration_ms": 10009.16256, "eligible_miss": 0.0, "miss": 0.0, "model": 119.0, "overflow": 0.0, "padding": 0.0, "tokens": 30464.0 }, { "bucket": 12080.0, "duration_ms": 10643.432062, "eligible_miss": 0.0, "miss": 9.0, "model": 56.0, "overflow": 9.0, "padding": 17.0, "tokens": 85791.0 }, { "bucket": 28928.0, "duration_ms": 9306.107722, "eligible_miss": 0.0, "miss": 2.0, "model": 115.0, "overflow": 2.0, "padding": 0.0, "tokens": 37973.0 }, { "bucket": 33792.0, "duration_ms": 10023.528799999996, "eligible_miss": 0.0, "miss": 0.0, "model": 132.0, "overflow": 0.0, "padding": 0.0, "tokens": 33792.0 }, { "bucket": 31744.0, "duration_ms": 10015.802693, "eligible_miss": 0.0, "miss": 0.0, "model": 124.0, "overflow": 0.0, "padding": 0.0, "tokens": 31744.0 }, { "bucket": 30464.0, "duration_ms": 9925.296385999996, "eligible_miss": 0.0, "miss": 0.0, "model": 119.0, "overflow": 0.0, "padding": 0.0, "tokens": 30464.0 }, { "bucket": 5072.0, "duration_ms": 9987.664447000003, "eligible_miss": 0.0, "miss": 12.0, "model": 32.0, "overflow": 12.0, "padding": 7.0, "tokens": 92449.0 }, { "bucket": 35584.0, "duration_ms": 9973.684404000003, "eligible_miss": 0.0, "miss": 0.0, "model": 139.0, "overflow": 0.0, "padding": 0.0, "tokens": 35584.0 }, { "bucket": 33024.0, "duration_ms": 10000.565399000006, "eligible_miss": 0.0, "miss": 0.0, "model": 129.0, "overflow": 0.0, "padding": 0.0, "tokens": 33024.0 } ], "clean": { "admitted": 2560, "completed": 2560, "completed_throughput_rps": 10.666666666666666, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 815867, "offered_rps": 10.666666666666666, "output_tokens": 1310720, "start_s": 60.0 }, "config": "C00", "drain_quarantined": false, "drain_seconds": 17.89816882798914, "latency_s": { "e2e": { "mean": 23.776247528639022, "n": 2560, "p50": 23.71122523449594, "p95": 24.185485272797813, "p99": 24.45216006551811 }, "tpot": { "mean": 0.04448661513129689, "n": 2560, "p50": 0.04432050637085125, "p95": 0.04553604761966451, "p99": 0.04615120161844849 }, "ttft": { "mean": 1.0435871965463093, "n": 2560, "p50": 1.0870295370114036, "p95": 1.2516038013927755, "p99": 1.5639317611194565 } }, "layer1": { "decode_tokens": 1322213, "kv_usage_max": 0.7301432819680995, "kv_usage_mean": 0.5031304572048997, "mode_counts": { "FULL": 5074, "NONE": 115, "PIECEWISE": 7 }, "mode_shares": { "FULL": 0.9765204003079292, "NONE": 0.022132409545804466, "PIECEWISE": 0.0013471901462663587 }, "preemptions": 0, "prefill_tokens": 818945, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 18, "queue_waiting_mean": 0.04157043879907621, "records_all": 8236, "records_clean": 5196, "requests_per_step": { "mean": 254.9688221709007, "n": 5196, "p50": 256.0, "p95": 256.0, "p99": 256.0 }, "scheduled_tokens_per_step": { "mean": 412.07813702848347, "n": 5196, "p50": 256.0, "p95": 256.0, "p99": 7964.100000000004 }, "step_duration_ms": { "mean": 92.26417854715166, "n": 5196, "p50": 78.5344495, "p95": 86.525586, "p99": 736.0913249500003 }, "token_efficiency_per_ms": 4.46628522051915 }, "layer2_missing_after_controller_cleanup": false, "load": "saturation", "pattern": "P02", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 3.45, "clean_c_waiting_median": 0.0, "completion_rate_rps": 0.0, "completion_rate_within_10pct": false, "tail_end_s": 337.7681430270022, "tail_start_s": 327.7681430270022, "valid": false, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 3.45, "clean_c_waiting_median": 0.0, "completion_rate_rps": 25.6, "completion_rate_within_10pct": false, "tail_end_s": 375.69639842701145, "tail_start_s": 365.69639842701145, "valid": false, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 2560, "run_dir": "runs/phase3/primary/P02-C00/saturation", "run_id": "P02-C00-saturation", "trace_files": 2, "waste": { "R128": 0.3723323346172142, "R32": 0.3612776759520059, "R64": 0.36868249852408347, "bucket_slack": 0.00011601748099157298, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.022132409545804466, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.022132409545804466, "padded_tokens_per_useful_token": 7.05225863761572e-05, "padding_fraction": 0.00011601748099157298 } }, "P03-C00-moderate": { "blocks": [ { "bucket": 434.0, "duration_ms": 9646.774494999996, "eligible_miss": 0.0, "miss": 7.0, "model": 414.0, "overflow": 7.0, "padding": 0.0, "tokens": 42391.0 }, { "bucket": 428.0, "duration_ms": 9324.853701000002, "eligible_miss": 0.0, "miss": 7.0, "model": 349.0, "overflow": 7.0, "padding": 0.0, "tokens": 45396.0 }, { "bucket": 451.0, "duration_ms": 9443.773851999995, "eligible_miss": 0.0, "miss": 7.0, "model": 377.0, "overflow": 7.0, "padding": 0.0, "tokens": 44779.0 }, { "bucket": 431.0, "duration_ms": 8789.258909999997, "eligible_miss": 0.0, "miss": 7.0, "model": 402.0, "overflow": 7.0, "padding": 0.0, "tokens": 39827.0 }, { "bucket": 444.0, "duration_ms": 8735.292183000001, "eligible_miss": 0.0, "miss": 7.0, "model": 425.0, "overflow": 7.0, "padding": 0.0, "tokens": 38560.0 }, { "bucket": 441.0, "duration_ms": 8991.055925999994, "eligible_miss": 0.0, "miss": 7.0, "model": 417.0, "overflow": 7.0, "padding": 0.0, "tokens": 40995.0 }, { "bucket": 423.0, "duration_ms": 9480.767129999997, "eligible_miss": 0.0, "miss": 7.0, "model": 381.0, "overflow": 7.0, "padding": 0.0, "tokens": 45023.0 }, { "bucket": 486.0, "duration_ms": 9729.935500999996, "eligible_miss": 0.0, "miss": 7.0, "model": 427.0, "overflow": 7.0, "padding": 0.0, "tokens": 44224.0 }, { "bucket": 416.0, "duration_ms": 9213.938557999996, "eligible_miss": 0.0, "miss": 7.0, "model": 384.0, "overflow": 7.0, "padding": 0.0, "tokens": 45373.0 }, { "bucket": 486.0, "duration_ms": 8918.107862000003, "eligible_miss": 0.0, "miss": 7.0, "model": 442.0, "overflow": 7.0, "padding": 0.0, "tokens": 39693.0 }, { "bucket": 409.0, "duration_ms": 9586.225367999996, "eligible_miss": 0.0, "miss": 8.0, "model": 392.0, "overflow": 8.0, "padding": 0.0, "tokens": 51207.0 }, { "bucket": 467.0, "duration_ms": 9515.115281000006, "eligible_miss": 0.0, "miss": 7.0, "model": 368.0, "overflow": 7.0, "padding": 0.0, "tokens": 44145.0 }, { "bucket": 414.0, "duration_ms": 8670.001719000002, "eligible_miss": 0.0, "miss": 7.0, "model": 398.0, "overflow": 7.0, "padding": 0.0, "tokens": 41341.0 }, { "bucket": 465.0, "duration_ms": 8769.038874999997, "eligible_miss": 0.0, "miss": 7.0, "model": 434.0, "overflow": 7.0, "padding": 0.0, "tokens": 39805.0 }, { "bucket": 434.0, "duration_ms": 9390.774539000004, "eligible_miss": 0.0, "miss": 7.0, "model": 375.0, "overflow": 7.0, "padding": 0.0, "tokens": 46322.0 }, { "bucket": 441.0, "duration_ms": 9182.554264, "eligible_miss": 0.0, "miss": 7.0, "model": 402.0, "overflow": 7.0, "padding": 0.0, "tokens": 43923.0 }, { "bucket": 460.0, "duration_ms": 8867.88750800001, "eligible_miss": 0.0, "miss": 7.0, "model": 400.0, "overflow": 7.0, "padding": 0.0, "tokens": 41579.0 }, { "bucket": 401.0, "duration_ms": 9142.820255999997, "eligible_miss": 0.0, "miss": 7.0, "model": 407.0, "overflow": 7.0, "padding": 0.0, "tokens": 44598.0 }, { "bucket": 485.0, "duration_ms": 9352.599022999993, "eligible_miss": 0.0, "miss": 7.0, "model": 402.0, "overflow": 7.0, "padding": 0.0, "tokens": 43986.0 }, { "bucket": 429.0, "duration_ms": 8637.459765999994, "eligible_miss": 0.0, "miss": 7.0, "model": 425.0, "overflow": 7.0, "padding": 0.0, "tokens": 40104.0 }, { "bucket": 448.0, "duration_ms": 9475.931046999996, "eligible_miss": 0.0, "miss": 7.0, "model": 386.0, "overflow": 7.0, "padding": 0.0, "tokens": 45960.0 }, { "bucket": 465.0, "duration_ms": 9328.015840000015, "eligible_miss": 0.0, "miss": 7.0, "model": 430.0, "overflow": 7.0, "padding": 0.0, "tokens": 43347.0 }, { "bucket": 439.0, "duration_ms": 9245.173080000004, "eligible_miss": 0.0, "miss": 8.0, "model": 411.0, "overflow": 8.0, "padding": 0.0, "tokens": 46942.0 }, { "bucket": 441.0, "duration_ms": 9031.702460999999, "eligible_miss": 0.0, "miss": 7.0, "model": 437.0, "overflow": 7.0, "padding": 0.0, "tokens": 41183.0 }, { "bucket": 439.0, "duration_ms": 8945.048207000003, "eligible_miss": 0.0, "miss": 7.0, "model": 426.0, "overflow": 7.0, "padding": 0.0, "tokens": 41666.0 }, { "bucket": 439.0, "duration_ms": 8656.631559, "eligible_miss": 0.0, "miss": 7.0, "model": 411.0, "overflow": 7.0, "padding": 0.0, "tokens": 40487.0 }, { "bucket": 438.0, "duration_ms": 8917.907948999997, "eligible_miss": 0.0, "miss": 7.0, "model": 400.0, "overflow": 7.0, "padding": 0.0, "tokens": 42512.0 }, { "bucket": 440.0, "duration_ms": 8937.543736000001, "eligible_miss": 0.0, "miss": 7.0, "model": 426.0, "overflow": 7.0, "padding": 0.0, "tokens": 42114.0 }, { "bucket": 441.0, "duration_ms": 8382.712513999999, "eligible_miss": 0.0, "miss": 7.0, "model": 440.0, "overflow": 7.0, "padding": 0.0, "tokens": 37512.0 }, { "bucket": 438.0, "duration_ms": 9172.430862000001, "eligible_miss": 0.0, "miss": 7.0, "model": 415.0, "overflow": 7.0, "padding": 0.0, "tokens": 43506.0 }, { "bucket": 460.0, "duration_ms": 9511.392210000004, "eligible_miss": 0.0, "miss": 7.0, "model": 407.0, "overflow": 7.0, "padding": 0.0, "tokens": 45333.0 }, { "bucket": 475.0, "duration_ms": 9785.702609, "eligible_miss": 0.0, "miss": 7.0, "model": 471.0, "overflow": 7.0, "padding": 0.0, "tokens": 44172.0 }, { "bucket": 439.0, "duration_ms": 8901.444294000008, "eligible_miss": 0.0, "miss": 7.0, "model": 426.0, "overflow": 7.0, "padding": 0.0, "tokens": 40862.0 }, { "bucket": 437.0, "duration_ms": 9806.976566000003, "eligible_miss": 0.0, "miss": 8.0, "model": 389.0, "overflow": 8.0, "padding": 0.0, "tokens": 52715.0 }, { "bucket": 440.0, "duration_ms": 8958.783222000005, "eligible_miss": 0.0, "miss": 7.0, "model": 409.0, "overflow": 7.0, "padding": 0.0, "tokens": 39756.0 }, { "bucket": 422.0, "duration_ms": 9178.061366000005, "eligible_miss": 0.0, "miss": 7.0, "model": 410.0, "overflow": 7.0, "padding": 0.0, "tokens": 44271.0 }, { "bucket": 425.0, "duration_ms": 8984.160134000002, "eligible_miss": 0.0, "miss": 7.0, "model": 355.0, "overflow": 7.0, "padding": 0.0, "tokens": 44663.0 }, { "bucket": 466.0, "duration_ms": 9250.503494999995, "eligible_miss": 0.0, "miss": 7.0, "model": 400.0, "overflow": 7.0, "padding": 0.0, "tokens": 43886.0 }, { "bucket": 444.0, "duration_ms": 8412.454728000006, "eligible_miss": 0.0, "miss": 7.0, "model": 449.0, "overflow": 7.0, "padding": 0.0, "tokens": 37387.0 }, { "bucket": 444.0, "duration_ms": 8843.111829, "eligible_miss": 0.0, "miss": 7.0, "model": 445.0, "overflow": 7.0, "padding": 0.0, "tokens": 40662.0 }, { "bucket": 428.0, "duration_ms": 9809.472161000005, "eligible_miss": 0.0, "miss": 7.0, "model": 375.0, "overflow": 7.0, "padding": 0.0, "tokens": 48958.0 }, { "bucket": 449.0, "duration_ms": 9674.471301999998, "eligible_miss": 0.0, "miss": 7.0, "model": 381.0, "overflow": 7.0, "padding": 0.0, "tokens": 47368.0 }, { "bucket": 441.0, "duration_ms": 9450.021538, "eligible_miss": 0.0, "miss": 7.0, "model": 380.0, "overflow": 7.0, "padding": 0.0, "tokens": 46428.0 }, { "bucket": 471.0, "duration_ms": 9220.409785000002, "eligible_miss": 0.0, "miss": 7.0, "model": 463.0, "overflow": 7.0, "padding": 0.0, "tokens": 41943.0 }, { "bucket": 453.0, "duration_ms": 8620.783462999989, "eligible_miss": 0.0, "miss": 7.0, "model": 450.0, "overflow": 7.0, "padding": 0.0, "tokens": 38619.0 }, { "bucket": 442.0, "duration_ms": 9088.896370999999, "eligible_miss": 0.0, "miss": 8.0, "model": 450.0, "overflow": 8.0, "padding": 0.0, "tokens": 43799.0 }, { "bucket": 410.0, "duration_ms": 9024.806824000001, "eligible_miss": 0.0, "miss": 7.0, "model": 369.0, "overflow": 7.0, "padding": 0.0, "tokens": 44660.0 }, { "bucket": 445.0, "duration_ms": 9384.437405000002, "eligible_miss": 0.0, "miss": 7.0, "model": 357.0, "overflow": 7.0, "padding": 0.0, "tokens": 46780.0 } ], "clean": { "admitted": 340, "completed": 339, "completed_throughput_rps": 1.4125, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 2054190, "offered_rps": 1.4166666666666667, "output_tokens": 21696, "start_s": 60.0 }, "config": "C00", "drain_quarantined": false, "drain_seconds": 0.4808295039983932, "latency_s": { "e2e": { "mean": 0.8583498531842609, "n": 339, "p50": 0.6899766309943516, "p95": 1.2946852156106616, "p99": 1.3524367231986252 }, "tpot": { "mean": 0.0073678705388819194, "n": 339, "p50": 0.005003864031528965, "p95": 0.01286850249975003, "p99": 0.01351572900346207 }, "ttft": { "mean": 0.3941740092347001, "n": 339, "p50": 0.38708334998227656, "p95": 0.5440592002210906, "p99": 0.5607605650188634 } }, "layer1": { "decode_tokens": 21402, "kv_usage_max": 0.053636117869694466, "kv_usage_mean": 0.0227916201009575, "mode_counts": { "FULL": 19249, "NONE": 726 }, "mode_shares": { "FULL": 0.9636545682102629, "NONE": 0.03634543178973717 }, "preemptions": 0, "prefill_tokens": 2059360, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 0, "queue_waiting_mean": 0.0, "records_all": 29343, "records_clean": 19975, "requests_per_step": { "mean": 1.0884605757196495, "n": 19975, "p50": 1.0, "p95": 2.0, "p99": 2.0 }, "scheduled_tokens_per_step": { "mean": 104.16831038798499, "n": 19975, "p50": 1.0, "p95": 2.0, "p99": 5737.759999999958 }, "step_duration_ms": { "mean": 21.996857135118898, "n": 19975, "p50": 9.367757, "p95": 12.816464299999998, "p99": 419.37568741999894 }, "token_efficiency_per_ms": 4.735599715364607 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P03", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 1.4, "clean_c_waiting_median": 0.0, "completion_rate_rps": 1.4, "completion_rate_within_10pct": true, "tail_end_s": 331.5279114540026, "tail_start_s": 321.5279114540026, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 1.4, "clean_c_waiting_median": 0.0, "completion_rate_rps": 1.4, "completion_rate_within_10pct": true, "tail_end_s": 363.4785102730093, "tail_start_s": 353.4785102730093, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": true, "requests_completed": 339, "run_dir": "runs/phase3/primary/P03-C00/moderate", "run_id": "P03-C00-moderate", "trace_files": 2, "waste": { "R128": 0.24734040984998104, "R32": 0.23857870988687485, "R64": 0.24443376797326863, "bucket_slack": 0.0, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.017356679769258258, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 138, "moe_layer_cv": null, "overflow_rate": 0.017356679769258258, "padded_tokens_per_useful_token": 0.0, "padding_fraction": 0.0 } }, "P03-C00-saturation": { "blocks": [ { "bucket": 864.0, "duration_ms": 10578.148114000001, "eligible_miss": 0.0, "miss": 10.0, "model": 28.0, "overflow": 10.0, "padding": 2.0, "tokens": 76404.0 }, { "duration_ms": 10051.067833, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 75648.0 }, { "duration_ms": 10430.060368999999, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 79159.0 }, { "bucket": 384.0, "duration_ms": 8947.849064999999, "eligible_miss": 0.0, "miss": 8.0, "model": 16.0, "overflow": 8.0, "padding": 0.0, "tokens": 61135.0 }, { "bucket": 864.0, "duration_ms": 11122.426039999998, "eligible_miss": 0.0, "miss": 11.0, "model": 29.0, "overflow": 11.0, "padding": 1.0, "tokens": 78761.0 }, { "duration_ms": 10057.831934, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 76555.0 }, { "duration_ms": 9721.105124000002, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73139.0 }, { "bucket": 48.0, "duration_ms": 9329.917999, "eligible_miss": 0.0, "miss": 9.0, "model": 10.0, "overflow": 9.0, "padding": 1.0, "tokens": 65693.0 }, { "bucket": 1200.0, "duration_ms": 10223.449019, "eligible_miss": 0.0, "miss": 10.0, "model": 35.0, "overflow": 10.0, "padding": 28.0, "tokens": 71110.0 }, { "duration_ms": 10493.838531000001, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 79030.0 }, { "duration_ms": 10439.288879, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81709.0 }, { "bucket": 56.0, "duration_ms": 9103.318499, "eligible_miss": 0.0, "miss": 9.0, "model": 10.0, "overflow": 9.0, "padding": 6.0, "tokens": 64928.0 }, { "bucket": 1680.0, "duration_ms": 10367.279989999999, "eligible_miss": 0.0, "miss": 11.0, "model": 35.0, "overflow": 11.0, "padding": 145.0, "tokens": 72060.0 }, { "duration_ms": 10189.229741, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 75842.0 }, { "duration_ms": 9478.008878, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 73062.0 }, { "bucket": 192.0, "duration_ms": 9436.550829999998, "eligible_miss": 0.0, "miss": 9.0, "model": 13.0, "overflow": 9.0, "padding": 0.0, "tokens": 65760.0 }, { "bucket": 1328.0, "duration_ms": 10334.733178, "eligible_miss": 0.0, "miss": 10.0, "model": 31.0, "overflow": 10.0, "padding": 89.0, "tokens": 70413.0 }, { "duration_ms": 10626.730527, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 81172.0 }, { "duration_ms": 9518.246487, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 72556.0 }, { "bucket": 48.0, "duration_ms": 9749.105485000002, "eligible_miss": 0.0, "miss": 9.0, "model": 10.0, "overflow": 9.0, "padding": 1.0, "tokens": 68945.0 }, { "bucket": 1152.0, "duration_ms": 10786.964422000001, "eligible_miss": 0.0, "miss": 10.0, "model": 34.0, "overflow": 10.0, "padding": 29.0, "tokens": 73567.0 }, { "bucket": 48.0, "duration_ms": 9785.572214, "eligible_miss": 0.0, "miss": 10.0, "model": 11.0, "overflow": 10.0, "padding": 3.0, "tokens": 76865.0 }, { "duration_ms": 9623.650463, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 72252.0 }, { "bucket": 48.0, "duration_ms": 10084.750344, "eligible_miss": 0.0, "miss": 10.0, "model": 11.0, "overflow": 10.0, "padding": 0.0, "tokens": 71946.0 }, { "bucket": 1104.0, "duration_ms": 10114.801081, "eligible_miss": 0.0, "miss": 10.0, "model": 33.0, "overflow": 10.0, "padding": 3.0, "tokens": 69776.0 }, { "bucket": 48.0, "duration_ms": 10094.120242, "eligible_miss": 0.0, "miss": 10.0, "model": 11.0, "overflow": 10.0, "padding": 2.0, "tokens": 73552.0 }, { "duration_ms": 10679.833572, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 80671.0 }, { "duration_ms": 9146.444671, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 67917.0 }, { "bucket": 1152.0, "duration_ms": 10535.819985999999, "eligible_miss": 0.0, "miss": 10.0, "model": 34.0, "overflow": 10.0, "padding": 75.0, "tokens": 69083.0 }, { "bucket": 48.0, "duration_ms": 9952.865603, "eligible_miss": 0.0, "miss": 10.0, "model": 11.0, "overflow": 10.0, "padding": 4.0, "tokens": 74679.0 }, { "bucket": 232.0, "duration_ms": 9606.608713999998, "eligible_miss": 0.0, "miss": 9.0, "model": 10.0, "overflow": 9.0, "padding": 6.0, "tokens": 71716.0 }, { "duration_ms": 10236.557004000002, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 78064.0 }, { "bucket": 1152.0, "duration_ms": 9876.530566, "eligible_miss": 0.0, "miss": 10.0, "model": 34.0, "overflow": 10.0, "padding": 18.0, "tokens": 63632.0 }, { "bucket": 48.0, "duration_ms": 9665.328617, "eligible_miss": 0.0, "miss": 10.0, "model": 11.0, "overflow": 10.0, "padding": 2.0, "tokens": 72669.0 }, { "duration_ms": 10083.804314, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 76205.0 }, { "duration_ms": 10325.771488, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 77498.0 }, { "bucket": 1200.0, "duration_ms": 9464.822698999998, "eligible_miss": 0.0, "miss": 8.0, "model": 33.0, "overflow": 8.0, "padding": 29.0, "tokens": 57502.0 }, { "duration_ms": 10398.848107000002, "eligible_miss": 0.0, "miss": 12.0, "model": 12.0, "overflow": 12.0, "tokens": 78851.0 }, { "duration_ms": 9908.080162, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 73838.0 }, { "duration_ms": 9995.163472999999, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 76673.0 }, { "bucket": 1152.0, "duration_ms": 10214.747484, "eligible_miss": 0.0, "miss": 9.0, "model": 33.0, "overflow": 9.0, "padding": 74.0, "tokens": 61305.0 }, { "bucket": 48.0, "duration_ms": 10312.275375000001, "eligible_miss": 0.0, "miss": 11.0, "model": 12.0, "overflow": 11.0, "padding": 3.0, "tokens": 79610.0 }, { "duration_ms": 9717.962814999999, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 74553.0 }, { "duration_ms": 10444.018532999999, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 82228.0 }, { "bucket": 1320.0, "duration_ms": 8902.236085, "eligible_miss": 0.0, "miss": 8.0, "model": 32.0, "overflow": 8.0, "padding": 148.0, "tokens": 52523.0 }, { "bucket": 48.0, "duration_ms": 10528.722166, "eligible_miss": 0.0, "miss": 11.0, "model": 12.0, "overflow": 11.0, "padding": 1.0, "tokens": 82473.0 }, { "duration_ms": 9880.531748000001, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 73322.0 }, { "duration_ms": 10429.997748999998, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 79679.0 } ], "clean": { "admitted": 567, "completed": 567, "completed_throughput_rps": 2.3625, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 3470825, "offered_rps": 2.3625, "output_tokens": 36288, "start_s": 60.0 }, "config": "C00", "drain_quarantined": false, "drain_seconds": 93.00942119900719, "latency_s": { "e2e": { "mean": 104.49926800635963, "n": 567, "p50": 108.49479436199181, "p95": 114.96174016330329, "p99": 125.03032377155616 }, "tpot": { "mean": 0.3016080685133144, "n": 567, "p50": 0.301236945777736, "p95": 0.3107678588207197, "p99": 0.3154822883366456 }, "ttft": { "mean": 85.49795969002082, "n": 567, "p50": 89.48056172500947, "p95": 96.23374651201881, "p99": 106.40916011528114 } }, "layer1": { "decode_tokens": 35902, "kv_usage_max": 0.9998918626655853, "kv_usage_mean": 0.9845854764583278, "mode_counts": { "FULL": 293, "NONE": 478, "PIECEWISE": 4 }, "mode_shares": { "FULL": 0.37806451612903225, "NONE": 0.6167741935483871, "PIECEWISE": 0.005161290322580645 }, "preemptions": 2, "prefill_tokens": 3469828, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 211, "queue_waiting_mean": 207.8516129032258, "records_all": 1540, "records_clean": 775, "requests_per_step": { "mean": 46.68258064516129, "n": 775, "p50": 47.0, "p95": 49.0, "p99": 50.0 }, "scheduled_tokens_per_step": { "mean": 4523.522580645162, "n": 775, "p50": 6175.0, "p95": 8192.0, "p99": 8192.0 }, "step_duration_ms": { "mean": 620.6387306051613, "n": 775, "p50": 802.754999, "p95": 1104.0022976999999, "p99": 1137.5921699 }, "token_efficiency_per_ms": 7.288495476642984 }, "layer2_missing_after_controller_cleanup": false, "load": "saturation", "pattern": "P03", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 2.3, "clean_c_waiting_median": 208.0, "completion_rate_rps": 2.5, "completion_rate_within_10pct": true, "tail_end_s": 336.5461640879803, "tail_start_s": 326.5461640879803, "valid": true, "waiting_median": 209.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 2.3, "clean_c_waiting_median": 208.0, "completion_rate_rps": 2.1, "completion_rate_within_10pct": true, "tail_end_s": 392.17679743198096, "tail_start_s": 382.17679743198096, "valid": true, "waiting_median": 209.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": true, "requests_completed": 567, "run_dir": "runs/phase3/primary/P03-C00/saturation", "run_id": "P03-C00-saturation", "trace_files": 2, "waste": { "R128": 0.24734040984998104, "R32": 0.23857870988687485, "R64": 0.24443376797326863, "bucket_slack": 0.043326435592343504, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.6167741935483871, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.6167741935483871, "padded_tokens_per_useful_token": 0.00019111568774549096, "padding_fraction": 0.043326435592343504 } }, "P03-C01-moderate": { "blocks": [ { "bucket": 954.0, "duration_ms": 9872.450652000009, "eligible_miss": 0.0, "miss": 23.0, "model": 332.0, "overflow": 23.0, "padding": 17.0, "tokens": 45821.0 }, { "bucket": 419.0, "duration_ms": 8502.870301999994, "eligible_miss": 0.0, "miss": 20.0, "model": 436.0, "overflow": 20.0, "padding": 0.0, "tokens": 33944.0 }, { "bucket": 537.0, "duration_ms": 8469.788425000002, "eligible_miss": 0.0, "miss": 19.0, "model": 398.0, "overflow": 19.0, "padding": 5.0, "tokens": 36476.0 }, { "bucket": 1330.0, "duration_ms": 9275.734582000001, "eligible_miss": 0.0, "miss": 23.0, "model": 353.0, "overflow": 23.0, "padding": 7.0, "tokens": 44107.0 }, { "bucket": 982.0, "duration_ms": 8895.486666, "eligible_miss": 0.0, "miss": 20.0, "model": 375.0, "overflow": 20.0, "padding": 8.0, "tokens": 40031.0 }, { "bucket": 394.0, "duration_ms": 8277.386265, "eligible_miss": 0.0, "miss": 20.0, "model": 394.0, "overflow": 20.0, "padding": 0.0, "tokens": 34398.0 }, { "bucket": 572.0, "duration_ms": 7978.012209000002, "eligible_miss": 0.0, "miss": 17.0, "model": 431.0, "overflow": 17.0, "padding": 8.0, "tokens": 32212.0 }, { "bucket": 832.0, "duration_ms": 8694.071453000006, "eligible_miss": 0.0, "miss": 21.0, "model": 403.0, "overflow": 21.0, "padding": 12.0, "tokens": 40122.0 }, { "bucket": 1315.0, "duration_ms": 8601.290529, "eligible_miss": 0.0, "miss": 18.0, "model": 385.0, "overflow": 18.0, "padding": 20.0, "tokens": 36044.0 }, { "bucket": 749.0, "duration_ms": 9269.075646999998, "eligible_miss": 0.0, "miss": 21.0, "model": 410.0, "overflow": 21.0, "padding": 11.0, "tokens": 39900.0 }, { "bucket": 374.0, "duration_ms": 9022.692624000003, "eligible_miss": 0.0, "miss": 22.0, "model": 388.0, "overflow": 22.0, "padding": 0.0, "tokens": 41430.0 }, { "bucket": 876.0, "duration_ms": 8708.543662000002, "eligible_miss": 0.0, "miss": 20.0, "model": 363.0, "overflow": 20.0, "padding": 0.0, "tokens": 39367.0 }, { "bucket": 1143.0, "duration_ms": 8555.031544999998, "eligible_miss": 0.0, "miss": 19.0, "model": 383.0, "overflow": 19.0, "padding": 0.0, "tokens": 36768.0 }, { "bucket": 1351.0, "duration_ms": 8710.897649000002, "eligible_miss": 0.0, "miss": 18.0, "model": 388.0, "overflow": 18.0, "padding": 23.0, "tokens": 37939.0 }, { "bucket": 415.0, "duration_ms": 9617.347848000003, "eligible_miss": 0.0, "miss": 24.0, "model": 382.0, "overflow": 24.0, "padding": 0.0, "tokens": 44403.0 }, { "bucket": 1146.0, "duration_ms": 8199.89401900001, "eligible_miss": 0.0, "miss": 18.0, "model": 400.0, "overflow": 18.0, "padding": 15.0, "tokens": 35088.0 }, { "bucket": 690.0, "duration_ms": 8341.056147, "eligible_miss": 0.0, "miss": 19.0, "model": 377.0, "overflow": 19.0, "padding": 2.0, "tokens": 35322.0 }, { "bucket": 938.0, "duration_ms": 8602.735985000012, "eligible_miss": 0.0, "miss": 19.0, "model": 384.0, "overflow": 19.0, "padding": 14.0, "tokens": 37364.0 }, { "bucket": 698.0, "duration_ms": 9105.636625000001, "eligible_miss": 0.0, "miss": 22.0, "model": 404.0, "overflow": 22.0, "padding": 3.0, "tokens": 40949.0 }, { "bucket": 368.0, "duration_ms": 9234.429309999998, "eligible_miss": 0.0, "miss": 23.0, "model": 357.0, "overflow": 23.0, "padding": 0.0, "tokens": 42032.0 }, { "bucket": 511.0, "duration_ms": 8338.672249999994, "eligible_miss": 0.0, "miss": 18.0, "model": 410.0, "overflow": 18.0, "padding": 5.0, "tokens": 33517.0 }, { "bucket": 707.0, "duration_ms": 8830.411349, "eligible_miss": 0.0, "miss": 20.0, "model": 376.0, "overflow": 20.0, "padding": 9.0, "tokens": 39809.0 }, { "bucket": 1006.0, "duration_ms": 9518.970913000003, "eligible_miss": 0.0, "miss": 22.0, "model": 387.0, "overflow": 22.0, "padding": 8.0, "tokens": 43905.0 }, { "bucket": 1026.0, "duration_ms": 7924.940408999995, "eligible_miss": 0.0, "miss": 17.0, "model": 399.0, "overflow": 17.0, "padding": 14.0, "tokens": 33149.0 }, { "bucket": 555.0, "duration_ms": 9312.925641999997, "eligible_miss": 0.0, "miss": 21.0, "model": 409.0, "overflow": 21.0, "padding": 6.0, "tokens": 38795.0 }, { "bucket": 390.0, "duration_ms": 8887.958122999997, "eligible_miss": 0.0, "miss": 21.0, "model": 408.0, "overflow": 21.0, "padding": 0.0, "tokens": 37762.0 }, { "bucket": 1043.0, "duration_ms": 9046.173872000007, "eligible_miss": 0.0, "miss": 22.0, "model": 370.0, "overflow": 22.0, "padding": 21.0, "tokens": 43066.0 }, { "bucket": 530.0, "duration_ms": 8635.939902999999, "eligible_miss": 0.0, "miss": 19.0, "model": 387.0, "overflow": 19.0, "padding": 11.0, "tokens": 36716.0 }, { "bucket": 507.0, "duration_ms": 8225.677353999987, "eligible_miss": 0.0, "miss": 17.0, "model": 458.0, "overflow": 17.0, "padding": 6.0, "tokens": 32360.0 }, { "bucket": 423.0, "duration_ms": 8624.490282999994, "eligible_miss": 0.0, "miss": 21.0, "model": 386.0, "overflow": 21.0, "padding": 7.0, "tokens": 39497.0 }, { "bucket": 773.0, "duration_ms": 8599.456987, "eligible_miss": 0.0, "miss": 21.0, "model": 378.0, "overflow": 21.0, "padding": 7.0, "tokens": 38376.0 }, { "bucket": 795.0, "duration_ms": 8423.488682999996, "eligible_miss": 0.0, "miss": 19.0, "model": 368.0, "overflow": 19.0, "padding": 10.0, "tokens": 36552.0 }, { "bucket": 551.0, "duration_ms": 8649.547544999992, "eligible_miss": 0.0, "miss": 19.0, "model": 411.0, "overflow": 19.0, "padding": 4.0, "tokens": 37170.0 }, { "bucket": 1765.0, "duration_ms": 8547.083584000002, "eligible_miss": 0.0, "miss": 18.0, "model": 429.0, "overflow": 18.0, "padding": 22.0, "tokens": 36596.0 }, { "bucket": 1128.0, "duration_ms": 8409.201042000006, "eligible_miss": 0.0, "miss": 19.0, "model": 382.0, "overflow": 19.0, "padding": 17.0, "tokens": 36807.0 }, { "bucket": 696.0, "duration_ms": 8875.711702000002, "eligible_miss": 0.0, "miss": 20.0, "model": 402.0, "overflow": 20.0, "padding": 1.0, "tokens": 36838.0 }, { "bucket": 679.0, "duration_ms": 9194.931754999994, "eligible_miss": 0.0, "miss": 21.0, "model": 398.0, "overflow": 21.0, "padding": 12.0, "tokens": 40277.0 }, { "bucket": 949.0, "duration_ms": 9227.201623999996, "eligible_miss": 0.0, "miss": 22.0, "model": 421.0, "overflow": 22.0, "padding": 6.0, "tokens": 41797.0 }, { "bucket": 864.0, "duration_ms": 8413.728965999999, "eligible_miss": 0.0, "miss": 19.0, "model": 392.0, "overflow": 19.0, "padding": 2.0, "tokens": 35228.0 }, { "bucket": 400.0, "duration_ms": 9326.991775000006, "eligible_miss": 0.0, "miss": 22.0, "model": 401.0, "overflow": 22.0, "padding": 0.0, "tokens": 40138.0 }, { "bucket": 369.0, "duration_ms": 8184.575214999996, "eligible_miss": 0.0, "miss": 20.0, "model": 384.0, "overflow": 20.0, "padding": 0.0, "tokens": 35391.0 }, { "bucket": 653.0, "duration_ms": 8893.912036999998, "eligible_miss": 0.0, "miss": 21.0, "model": 402.0, "overflow": 21.0, "padding": 3.0, "tokens": 40808.0 }, { "bucket": 379.0, "duration_ms": 8951.537339, "eligible_miss": 0.0, "miss": 21.0, "model": 366.0, "overflow": 21.0, "padding": 0.0, "tokens": 39206.0 }, { "bucket": 494.0, "duration_ms": 9136.155221999994, "eligible_miss": 0.0, "miss": 22.0, "model": 353.0, "overflow": 22.0, "padding": 6.0, "tokens": 41596.0 }, { "bucket": 1440.0, "duration_ms": 8599.284305000006, "eligible_miss": 0.0, "miss": 18.0, "model": 444.0, "overflow": 18.0, "padding": 12.0, "tokens": 33942.0 }, { "bucket": 898.0, "duration_ms": 8410.183011000001, "eligible_miss": 0.0, "miss": 21.0, "model": 401.0, "overflow": 21.0, "padding": 14.0, "tokens": 38166.0 }, { "bucket": 380.0, "duration_ms": 8305.505917999999, "eligible_miss": 0.0, "miss": 19.0, "model": 396.0, "overflow": 19.0, "padding": 1.0, "tokens": 35656.0 }, { "bucket": 373.0, "duration_ms": 9378.466820000003, "eligible_miss": 0.0, "miss": 22.0, "model": 368.0, "overflow": 22.0, "padding": 0.0, "tokens": 42144.0 } ], "clean": { "admitted": 300, "completed": 300, "completed_throughput_rps": 1.25, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 1816359, "offered_rps": 1.25, "output_tokens": 19200, "start_s": 60.0 }, "config": "C01", "drain_quarantined": false, "drain_seconds": 0.8021622190135531, "latency_s": { "e2e": { "mean": 0.8661587820320468, "n": 300, "p50": 0.72734198148828, "p95": 1.3885476594397914, "p99": 1.4521425597564666 }, "tpot": { "mean": 0.006679995698883892, "n": 300, "p50": 0.004638713563696319, "p95": 0.012775019008808564, "p99": 0.01396566546533168 }, "ttft": { "mean": 0.4453190530023615, "n": 300, "p50": 0.43017592300020624, "p95": 0.6033891130937263, "p99": 0.6222539604848134 } }, "layer1": { "decode_tokens": 18903, "kv_usage_max": 0.052805456386209815, "kv_usage_mean": 0.021045833023510395, "mode_counts": { "FULL": 17787, "NONE": 1377, "PIECEWISE": 74 }, "mode_shares": { "FULL": 0.9245763592889074, "NONE": 0.07157708701528226, "PIECEWISE": 0.0038465536958103754 }, "preemptions": 0, "prefill_tokens": 1820078, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 0, "queue_waiting_mean": 0.0, "records_all": 28339, "records_clean": 19238, "requests_per_step": { "mean": 1.0367501819315936, "n": 19238, "p50": 1.0, "p95": 2.0, "p99": 2.0 }, "scheduled_tokens_per_step": { "mean": 95.59106975777108, "n": 19238, "p50": 1.0, "p95": 537.6999999999607, "p99": 2048.0 }, "step_duration_ms": { "mean": 21.87376836323942, "n": 19238, "p50": 9.320138, "p95": 120.27652529999995, "p99": 301.36491193000046 }, "token_efficiency_per_ms": 4.370123527431119 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P03", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 1.2, "clean_c_waiting_median": 0.0, "completion_rate_rps": 1.3, "completion_rate_within_10pct": true, "tail_end_s": 331.3140532330144, "tail_start_s": 321.3140532330144, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 1.2, "clean_c_waiting_median": 0.0, "completion_rate_rps": 1.3, "completion_rate_within_10pct": true, "tail_end_s": 364.91858237600536, "tail_start_s": 354.91858237600536, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": true, "requests_completed": 300, "run_dir": "runs/phase3/primary/P03-C01/moderate", "run_id": "P03-C01-moderate", "trace_files": 2, "waste": { "R128": 0.24734040984998104, "R32": 0.23857870988687485, "R64": 0.24443376797326863, "bucket_slack": 0.009596612313361013, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.05141005895161719, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 300, "moe_layer_cv": null, "overflow_rate": 0.05141005895161719, "padded_tokens_per_useful_token": 0.0001897790134862731, "padding_fraction": 0.009596612313361013 } }, "P03-C01-saturation": { "blocks": [ { "duration_ms": 9820.830930999999, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 10156.821435, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 9768.233745000001, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 10029.871413, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 10104.615715, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 10001.748752999998, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 10084.706814999998, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 9894.45056, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 9969.729338, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 10040.877489, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 10181.284094999999, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 9734.640943000002, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 9962.477245, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 10118.299278000002, "eligible_miss": 0.0, "miss": 33.0, "model": 33.0, "overflow": 33.0, "tokens": 67584.0 }, { "duration_ms": 10158.388776, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 9947.161227999999, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 9926.129196000002, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 9810.286340000002, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 10265.503908, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 9898.772765000002, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 10055.452221000001, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 10027.743997000001, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 9891.145452, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 10007.204138, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 10029.236173999998, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 9957.308014, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 10010.737170999999, "eligible_miss": 0.0, "miss": 33.0, "model": 33.0, "overflow": 33.0, "tokens": 67584.0 }, { "duration_ms": 9880.398545000002, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 10086.817054999998, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 10050.369225999999, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 9883.463523999999, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 9874.166397, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 10038.898957000001, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 10046.80094, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 10222.667140000001, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 9848.842729000002, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 10060.680079, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 9929.31106, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 9840.875362, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 10192.831885999998, "eligible_miss": 0.0, "miss": 33.0, "model": 33.0, "overflow": 33.0, "tokens": 67584.0 }, { "duration_ms": 9823.413677999997, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 10218.273869000002, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 10057.724521999999, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 9842.506709000001, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 9849.893720999997, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 10006.143056999997, "eligible_miss": 0.0, "miss": 31.0, "model": 31.0, "overflow": 31.0, "tokens": 63488.0 }, { "duration_ms": 10209.053572, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 }, { "duration_ms": 10185.623811000001, "eligible_miss": 0.0, "miss": 32.0, "model": 32.0, "overflow": 32.0, "tokens": 65536.0 } ], "clean": { "admitted": 501, "completed": 501, "completed_throughput_rps": 2.0875, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 3073055, "offered_rps": 2.0875, "output_tokens": 32064, "start_s": 60.0 }, "config": "C01", "drain_quarantined": false, "drain_seconds": 115.08961504499894, "latency_s": { "e2e": { "mean": 113.99268500659687, "n": 501, "p50": 121.33762379398104, "p95": 124.57225271401694, "p99": 129.85229865298606 }, "tpot": { "mean": 0.15808895612808507, "n": 501, "p50": 0.15828559920607535, "p95": 0.16043450426964445, "p99": 0.1609802155396051 }, "ttft": { "mean": 104.03308077052752, "n": 501, "p50": 111.41430233599385, "p95": 114.49460457300302, "p99": 120.11279526297585 } }, "layer1": { "decode_tokens": 31537, "kv_usage_max": 0.46842862471359303, "kv_usage_mean": 0.4521710693825813, "mode_counts": { "NONE": 1516 }, "mode_shares": { "NONE": 1.0 }, "preemptions": 0, "prefill_tokens": 3073231, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 236, "queue_waiting_mean": 233.20712401055408, "records_all": 3106, "records_clean": 1516, "requests_per_step": { "mean": 22.131926121372032, "n": 1516, "p50": 22.0, "p95": 24.0, "p99": 24.0 }, "scheduled_tokens_per_step": { "mean": 2048.0, "n": 1516, "p50": 2048.0, "p95": 2048.0, "p99": 2048.0 }, "step_duration_ms": { "mean": 316.6242829643799, "n": 1516, "p50": 311.66107999999997, "p95": 358.29868250000004, "p99": 374.21161494999996 }, "token_efficiency_per_ms": 6.468234150664935 }, "layer2_missing_after_controller_cleanup": false, "load": "saturation", "pattern": "P03", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 2.0, "clean_c_waiting_median": 233.0, "completion_rate_rps": 2.1, "completion_rate_within_10pct": true, "tail_end_s": 348.87919582100585, "tail_start_s": 338.87919582100585, "valid": true, "waiting_median": 234.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 2.0, "clean_c_waiting_median": 233.0, "completion_rate_rps": 1.9, "completion_rate_within_10pct": true, "tail_end_s": 398.6435712639941, "tail_start_s": 388.6435712639941, "valid": true, "waiting_median": 235.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": true, "requests_completed": 501, "run_dir": "runs/phase3/primary/P03-C01/saturation", "run_id": "P03-C01-saturation", "trace_files": 2, "waste": { "R128": 0.24734040984998104, "R32": 0.23857870988687485, "R64": 0.24443376797326863, "bucket_slack": 0.0, "eligible_miss_rate": 0.0, "graph_miss_rate": 1.0, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 1.0, "padded_tokens_per_useful_token": 0.0, "padding_fraction": 0.0 } }, "P03-C10-moderate": { "blocks": [ { "bucket": 432.0, "duration_ms": 8606.451834000003, "eligible_miss": 0.0, "miss": 7.0, "model": 426.0, "overflow": 7.0, "padding": 0.0, "tokens": 39915.0 }, { "bucket": 390.0, "duration_ms": 9059.634061, "eligible_miss": 0.0, "miss": 7.0, "model": 364.0, "overflow": 7.0, "padding": 0.0, "tokens": 45757.0 }, { "bucket": 469.0, "duration_ms": 9428.323844999995, "eligible_miss": 0.0, "miss": 7.0, "model": 391.0, "overflow": 7.0, "padding": 0.0, "tokens": 45103.0 }, { "bucket": 430.0, "duration_ms": 8757.352923000006, "eligible_miss": 0.0, "miss": 7.0, "model": 413.0, "overflow": 7.0, "padding": 0.0, "tokens": 41620.0 }, { "bucket": 428.0, "duration_ms": 8500.626963000002, "eligible_miss": 0.0, "miss": 7.0, "model": 435.0, "overflow": 7.0, "padding": 0.0, "tokens": 38894.0 }, { "bucket": 427.0, "duration_ms": 8880.6502, "eligible_miss": 0.0, "miss": 7.0, "model": 422.0, "overflow": 7.0, "padding": 0.0, "tokens": 41868.0 }, { "bucket": 447.0, "duration_ms": 8893.951561999991, "eligible_miss": 0.0, "miss": 7.0, "model": 410.0, "overflow": 7.0, "padding": 0.0, "tokens": 41639.0 }, { "bucket": 433.0, "duration_ms": 9634.180625000006, "eligible_miss": 0.0, "miss": 7.0, "model": 406.0, "overflow": 7.0, "padding": 0.0, "tokens": 46751.0 }, { "bucket": 452.0, "duration_ms": 9403.595920000002, "eligible_miss": 0.0, "miss": 7.0, "model": 411.0, "overflow": 7.0, "padding": 0.0, "tokens": 45103.0 }, { "bucket": 462.0, "duration_ms": 8918.339332999998, "eligible_miss": 0.0, "miss": 7.0, "model": 425.0, "overflow": 7.0, "padding": 0.0, "tokens": 40754.0 }, { "bucket": 394.0, "duration_ms": 8755.985819000001, "eligible_miss": 0.0, "miss": 7.0, "model": 401.0, "overflow": 7.0, "padding": 0.0, "tokens": 42715.0 }, { "bucket": 437.0, "duration_ms": 9270.625737000002, "eligible_miss": 0.0, "miss": 7.0, "model": 355.0, "overflow": 7.0, "padding": 0.0, "tokens": 46240.0 }, { "bucket": 476.0, "duration_ms": 8676.071426000004, "eligible_miss": 0.0, "miss": 7.0, "model": 456.0, "overflow": 7.0, "padding": 0.0, "tokens": 38226.0 }, { "bucket": 425.0, "duration_ms": 8864.808441000001, "eligible_miss": 0.0, "miss": 7.0, "model": 389.0, "overflow": 7.0, "padding": 0.0, "tokens": 43130.0 }, { "bucket": 447.0, "duration_ms": 8940.273261999997, "eligible_miss": 0.0, "miss": 7.0, "model": 403.0, "overflow": 7.0, "padding": 0.0, "tokens": 42214.0 }, { "bucket": 392.0, "duration_ms": 9269.719275, "eligible_miss": 0.0, "miss": 7.0, "model": 368.0, "overflow": 7.0, "padding": 0.0, "tokens": 46632.0 }, { "bucket": 477.0, "duration_ms": 9106.583498999991, "eligible_miss": 0.0, "miss": 7.0, "model": 415.0, "overflow": 7.0, "padding": 0.0, "tokens": 42267.0 }, { "bucket": 426.0, "duration_ms": 8750.417243000005, "eligible_miss": 0.0, "miss": 7.0, "model": 418.0, "overflow": 7.0, "padding": 0.0, "tokens": 41424.0 }, { "bucket": 422.0, "duration_ms": 9814.590544999997, "eligible_miss": 0.0, "miss": 7.0, "model": 370.0, "overflow": 7.0, "padding": 0.0, "tokens": 49275.0 }, { "bucket": 442.0, "duration_ms": 8302.109783000002, "eligible_miss": 0.0, "miss": 7.0, "model": 431.0, "overflow": 7.0, "padding": 0.0, "tokens": 37646.0 }, { "bucket": 464.0, "duration_ms": 9556.731577999999, "eligible_miss": 0.0, "miss": 7.0, "model": 417.0, "overflow": 7.0, "padding": 0.0, "tokens": 44464.0 }, { "bucket": 433.0, "duration_ms": 9108.740321000001, "eligible_miss": 0.0, "miss": 7.0, "model": 416.0, "overflow": 7.0, "padding": 0.0, "tokens": 43313.0 }, { "bucket": 404.0, "duration_ms": 8835.236437, "eligible_miss": 0.0, "miss": 7.0, "model": 387.0, "overflow": 7.0, "padding": 0.0, "tokens": 43111.0 }, { "bucket": 462.0, "duration_ms": 9117.118130000004, "eligible_miss": 0.0, "miss": 7.0, "model": 435.0, "overflow": 7.0, "padding": 0.0, "tokens": 42209.0 }, { "bucket": 427.0, "duration_ms": 8578.996583000004, "eligible_miss": 0.0, "miss": 7.0, "model": 434.0, "overflow": 7.0, "padding": 0.0, "tokens": 39814.0 }, { "bucket": 434.0, "duration_ms": 9440.617024000001, "eligible_miss": 0.0, "miss": 7.0, "model": 423.0, "overflow": 7.0, "padding": 0.0, "tokens": 45136.0 }, { "bucket": 467.0, "duration_ms": 8027.303883, "eligible_miss": 0.0, "miss": 7.0, "model": 444.0, "overflow": 7.0, "padding": 0.0, "tokens": 34783.0 }, { "bucket": 418.0, "duration_ms": 9118.96389, "eligible_miss": 0.0, "miss": 7.0, "model": 385.0, "overflow": 7.0, "padding": 0.0, "tokens": 44885.0 }, { "bucket": 439.0, "duration_ms": 8908.081147, "eligible_miss": 0.0, "miss": 7.0, "model": 423.0, "overflow": 7.0, "padding": 0.0, "tokens": 41711.0 }, { "bucket": 440.0, "duration_ms": 8775.029561000003, "eligible_miss": 0.0, "miss": 7.0, "model": 445.0, "overflow": 7.0, "padding": 0.0, "tokens": 40126.0 }, { "bucket": 428.0, "duration_ms": 8871.548213000005, "eligible_miss": 0.0, "miss": 7.0, "model": 395.0, "overflow": 7.0, "padding": 0.0, "tokens": 42209.0 }, { "bucket": 447.0, "duration_ms": 9716.337356000007, "eligible_miss": 0.0, "miss": 7.0, "model": 417.0, "overflow": 7.0, "padding": 0.0, "tokens": 46643.0 }, { "bucket": 439.0, "duration_ms": 9210.914279, "eligible_miss": 0.0, "miss": 7.0, "model": 442.0, "overflow": 7.0, "padding": 0.0, "tokens": 42681.0 }, { "bucket": 435.0, "duration_ms": 9027.704484999998, "eligible_miss": 0.0, "miss": 7.0, "model": 427.0, "overflow": 7.0, "padding": 0.0, "tokens": 42068.0 }, { "bucket": 443.0, "duration_ms": 9020.085927, "eligible_miss": 0.0, "miss": 7.0, "model": 393.0, "overflow": 7.0, "padding": 0.0, "tokens": 42897.0 }, { "bucket": 437.0, "duration_ms": 8676.806239999987, "eligible_miss": 0.0, "miss": 7.0, "model": 421.0, "overflow": 7.0, "padding": 0.0, "tokens": 40757.0 }, { "bucket": 429.0, "duration_ms": 9518.529198999995, "eligible_miss": 0.0, "miss": 7.0, "model": 384.0, "overflow": 7.0, "padding": 0.0, "tokens": 46872.0 }, { "bucket": 447.0, "duration_ms": 9277.076311999992, "eligible_miss": 0.0, "miss": 7.0, "model": 395.0, "overflow": 7.0, "padding": 0.0, "tokens": 45053.0 }, { "bucket": 437.0, "duration_ms": 8869.813008000003, "eligible_miss": 0.0, "miss": 7.0, "model": 409.0, "overflow": 7.0, "padding": 0.0, "tokens": 41382.0 }, { "bucket": 440.0, "duration_ms": 8463.263412999995, "eligible_miss": 0.0, "miss": 7.0, "model": 447.0, "overflow": 7.0, "padding": 0.0, "tokens": 38229.0 }, { "bucket": 438.0, "duration_ms": 9138.376169, "eligible_miss": 0.0, "miss": 7.0, "model": 440.0, "overflow": 7.0, "padding": 0.0, "tokens": 42630.0 }, { "bucket": 436.0, "duration_ms": 9575.711637000006, "eligible_miss": 0.0, "miss": 7.0, "model": 373.0, "overflow": 7.0, "padding": 0.0, "tokens": 47360.0 }, { "bucket": 411.0, "duration_ms": 9973.924517000007, "eligible_miss": 0.0, "miss": 7.0, "model": 375.0, "overflow": 7.0, "padding": 0.0, "tokens": 49974.0 }, { "bucket": 464.0, "duration_ms": 9111.179539000006, "eligible_miss": 0.0, "miss": 7.0, "model": 403.0, "overflow": 7.0, "padding": 0.0, "tokens": 43252.0 }, { "bucket": 441.0, "duration_ms": 8938.893511999999, "eligible_miss": 0.0, "miss": 7.0, "model": 448.0, "overflow": 7.0, "padding": 0.0, "tokens": 41598.0 }, { "bucket": 440.0, "duration_ms": 8203.012773, "eligible_miss": 0.0, "miss": 7.0, "model": 440.0, "overflow": 7.0, "padding": 0.0, "tokens": 36589.0 }, { "bucket": 441.0, "duration_ms": 8994.393566000004, "eligible_miss": 0.0, "miss": 7.0, "model": 448.0, "overflow": 7.0, "padding": 0.0, "tokens": 41980.0 }, { "bucket": 438.0, "duration_ms": 8992.481718000001, "eligible_miss": 0.0, "miss": 7.0, "model": 378.0, "overflow": 7.0, "padding": 0.0, "tokens": 43403.0 } ], "clean": { "admitted": 336, "completed": 335, "completed_throughput_rps": 1.3958333333333333, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 2025114, "offered_rps": 1.4, "output_tokens": 21440, "start_s": 60.0 }, "config": "C10", "drain_quarantined": false, "drain_seconds": 0.38259596601710655, "latency_s": { "e2e": { "mean": 0.8324871015964326, "n": 335, "p50": 0.6860202910029329, "p95": 1.280704226004309, "p99": 1.3414597219065765 }, "tpot": { "mean": 0.006963377769765788, "n": 335, "p50": 0.004799242444162715, "p95": 0.012645531087071591, "p99": 0.013250505485588551 }, "ttft": { "mean": 0.39379430210118793, "n": 335, "p50": 0.3876922279887367, "p95": 0.5416871845984134, "p99": 0.5613275917002466 } }, "layer1": { "decode_tokens": 21106, "kv_usage_max": 0.04955540013987414, "kv_usage_mean": 0.02050982433691785, "mode_counts": { "FULL": 19417, "NONE": 754 }, "mode_shares": { "FULL": 0.9626196023994844, "NONE": 0.03738039760051559 }, "preemptions": 0, "prefill_tokens": 2031196, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 0, "queue_waiting_mean": 0.0, "records_all": 29662, "records_clean": 20171, "requests_per_step": { "mean": 1.0630112537801795, "n": 20171, "p50": 1.0, "p95": 2.0, "p99": 2.0 }, "scheduled_tokens_per_step": { "mean": 101.74517872192752, "n": 20171, "p50": 1.0, "p95": 2.0, "p99": 5678.799999999996 }, "step_duration_ms": { "mean": 21.460570259927618, "n": 20171, "p50": 9.324558, "p95": 12.3158005, "p99": 413.3298498999996 }, "token_efficiency_per_ms": 4.741028662780309 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P03", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 1.4, "clean_c_waiting_median": 0.0, "completion_rate_rps": 1.4, "completion_rate_within_10pct": true, "tail_end_s": 331.6514889940154, "tail_start_s": 321.6514889940154, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 1.4, "clean_c_waiting_median": 0.0, "completion_rate_rps": 1.3, "completion_rate_within_10pct": true, "tail_end_s": 363.1196642330033, "tail_start_s": 353.1196642330033, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": true, "requests_completed": 335, "run_dir": "runs/phase3/primary/P03-C10/moderate", "run_id": "P03-C10-moderate", "trace_files": 2, "waste": { "R128": 0.24734040984998104, "R32": 0.23857870988687485, "R64": 0.24443376797326863, "bucket_slack": 0.0, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.017010074419075583, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 119, "moe_layer_cv": null, "overflow_rate": 0.017010074419075583, "padded_tokens_per_useful_token": 0.0, "padding_fraction": 0.0 } }, "P03-C10-saturation": { "blocks": [ { "duration_ms": 9687.455152999999, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 72210.0 }, { "bucket": 1344.0, "duration_ms": 9426.609795999999, "eligible_miss": 0.0, "miss": 9.0, "model": 33.0, "overflow": 9.0, "padding": 73.0, "tokens": 61098.0 }, { "duration_ms": 10645.066627999999, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 79262.0 }, { "duration_ms": 9608.448556000001, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73519.0 }, { "duration_ms": 9842.591738, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "bucket": 1288.0, "duration_ms": 9692.898608, "eligible_miss": 1.0, "miss": 9.0, "model": 32.0, "overflow": 8.0, "padding": 93.0, "tokens": 60966.0 }, { "bucket": 56.0, "duration_ms": 10264.24747, "eligible_miss": 0.0, "miss": 10.0, "model": 11.0, "overflow": 10.0, "padding": 7.0, "tokens": 78457.0 }, { "duration_ms": 9965.624573000001, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 73288.0 }, { "duration_ms": 10783.808192, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81663.0 }, { "bucket": 56.0, "duration_ms": 9027.21859, "eligible_miss": 0.0, "miss": 8.0, "model": 9.0, "overflow": 8.0, "padding": 4.0, "tokens": 65280.0 }, { "bucket": 1288.0, "duration_ms": 10933.014086, "eligible_miss": 0.0, "miss": 11.0, "model": 34.0, "overflow": 11.0, "padding": 94.0, "tokens": 76868.0 }, { "duration_ms": 9168.627825000001, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 66834.0 }, { "duration_ms": 10701.607950000001, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 84747.0 }, { "duration_ms": 9832.589772000001, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "bucket": 1232.0, "duration_ms": 9859.522224, "eligible_miss": 0.0, "miss": 10.0, "model": 32.0, "overflow": 10.0, "padding": 68.0, "tokens": 63071.0 }, { "duration_ms": 10355.40541, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 77397.0 }, { "duration_ms": 9731.559735, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 72054.0 }, { "duration_ms": 9761.415851000002, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73079.0 }, { "bucket": 1120.0, "duration_ms": 9693.590346999998, "eligible_miss": 0.0, "miss": 9.0, "model": 29.0, "overflow": 9.0, "padding": 61.0, "tokens": 65714.0 }, { "bucket": 112.0, "duration_ms": 10225.390153999999, "eligible_miss": 0.0, "miss": 11.0, "model": 13.0, "overflow": 11.0, "padding": 9.0, "tokens": 72902.0 }, { "duration_ms": 10017.791458, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 73933.0 }, { "duration_ms": 9772.353466, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 75807.0 }, { "duration_ms": 10337.735919, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 79175.0 }, { "bucket": 1176.0, "duration_ms": 10061.821364, "eligible_miss": 0.0, "miss": 10.0, "model": 31.0, "overflow": 10.0, "padding": 107.0, "tokens": 63691.0 }, { "duration_ms": 10157.843276000001, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 76081.0 }, { "bucket": 56.0, "duration_ms": 9907.907284, "eligible_miss": 0.0, "miss": 9.0, "model": 10.0, "overflow": 9.0, "padding": 6.0, "tokens": 72726.0 }, { "duration_ms": 10674.836298999999, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 79153.0 }, { "bucket": 1208.0, "duration_ms": 8919.901420000002, "eligible_miss": 0.0, "miss": 8.0, "model": 30.0, "overflow": 8.0, "padding": 134.0, "tokens": 57723.0 }, { "duration_ms": 10437.981232999999, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 78297.0 }, { "bucket": 56.0, "duration_ms": 9764.594819999998, "eligible_miss": 0.0, "miss": 10.0, "model": 11.0, "overflow": 10.0, "padding": 7.0, "tokens": 73149.0 }, { "duration_ms": 10628.824848, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 80667.0 }, { "bucket": 392.0, "duration_ms": 8582.760878000003, "eligible_miss": 0.0, "miss": 8.0, "model": 15.0, "overflow": 8.0, "padding": 35.0, "tokens": 57310.0 }, { "bucket": 784.0, "duration_ms": 11258.554805000002, "eligible_miss": 0.0, "miss": 12.0, "model": 26.0, "overflow": 12.0, "padding": 73.0, "tokens": 81615.0 }, { "duration_ms": 9436.909324000002, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 69553.0 }, { "duration_ms": 10436.931808, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 79108.0 }, { "duration_ms": 9560.4529, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 69775.0 }, { "bucket": 1176.0, "duration_ms": 9651.965396, "eligible_miss": 0.0, "miss": 9.0, "model": 30.0, "overflow": 9.0, "padding": 113.0, "tokens": 61029.0 }, { "duration_ms": 10305.695789, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 78692.0 }, { "bucket": 48.0, "duration_ms": 10496.442815, "eligible_miss": 0.0, "miss": 10.0, "model": 11.0, "overflow": 10.0, "padding": 0.0, "tokens": 77771.0 }, { "duration_ms": 9699.25625, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 72736.0 }, { "bucket": 944.0, "duration_ms": 9765.820548, "eligible_miss": 0.0, "miss": 9.0, "model": 26.0, "overflow": 9.0, "padding": 97.0, "tokens": 61021.0 }, { "bucket": 168.0, "duration_ms": 10234.118829, "eligible_miss": 0.0, "miss": 11.0, "model": 14.0, "overflow": 11.0, "padding": 21.0, "tokens": 77813.0 }, { "duration_ms": 10091.831287, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 73848.0 }, { "duration_ms": 9733.236188, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 75878.0 }, { "duration_ms": 10696.939206, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 80674.0 }, { "bucket": 1120.0, "duration_ms": 9454.301014, "eligible_miss": 0.0, "miss": 10.0, "model": 30.0, "overflow": 10.0, "padding": 68.0, "tokens": 59155.0 }, { "duration_ms": 11414.313313, "eligible_miss": 1.0, "miss": 9.0, "model": 9.0, "overflow": 8.0, "tokens": 65885.0 }, { "duration_ms": 8901.841632, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 71890.0 } ], "clean": { "admitted": 559, "completed": 559, "completed_throughput_rps": 2.3291666666666666, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 3429894, "offered_rps": 2.3291666666666666, "output_tokens": 35776, "start_s": 60.0 }, "config": "C10", "drain_quarantined": false, "drain_seconds": 91.29178713698639, "latency_s": { "e2e": { "mean": 105.03485774811313, "n": 559, "p50": 108.84702699899208, "p95": 118.28994776179317, "p99": 126.86703993751374 }, "tpot": { "mean": 0.32836759844498487, "n": 559, "p50": 0.3280060368410814, "p95": 0.33947711540307546, "p99": 0.3471749682567315 }, "ttft": { "mean": 84.34769904607909, "n": 559, "p50": 88.07736104700598, "p95": 97.8547530898999, "p99": 106.90823322451381 } }, "layer1": { "decode_tokens": 35621, "kv_usage_max": 1.0, "kv_usage_mean": 0.9860734670273078, "mode_counts": { "FULL": 244, "NONE": 474 }, "mode_shares": { "FULL": 0.3398328690807799, "NONE": 0.6601671309192201 }, "preemptions": 1, "prefill_tokens": 3434399, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 207, "queue_waiting_mean": 203.81337047353762, "records_all": 1456, "records_clean": 718, "requests_per_step": { "mean": 50.63091922005571, "n": 718, "p50": 51.0, "p95": 53.0, "p99": 53.0 }, "scheduled_tokens_per_step": { "mean": 4832.896935933148, "n": 718, "p50": 6751.0, "p95": 8192.0, "p99": 8192.0 }, "step_duration_ms": { "mean": 667.980022321727, "n": 718, "p50": 875.1449805, "p95": 1118.2583134, "p99": 1146.5907156899998 }, "token_efficiency_per_ms": 7.235092030350308 }, "layer2_missing_after_controller_cleanup": true, "load": "saturation", "pattern": "P03", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 2.3499999999999996, "clean_c_waiting_median": 204.0, "completion_rate_rps": 2.1, "completion_rate_within_10pct": false, "tail_end_s": 356.32926020701416, "tail_start_s": 346.32926020701416, "valid": false, "waiting_median": 206.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 2.3499999999999996, "clean_c_waiting_median": 204.0, "completion_rate_rps": 2.1, "completion_rate_within_10pct": false, "tail_end_s": 417.3262625900097, "tail_start_s": 407.3262625900097, "valid": false, "waiting_median": 205.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 559, "run_dir": "runs/phase3/primary/P03-C10/saturation", "run_id": "P03-C10-saturation", "trace_files": 0, "waste": { "R128": 0.24734040984998104, "R32": 0.23857870988687485, "R64": 0.24443376797326863, "bucket_slack": 0.07603458049886622, "eligible_miss_rate": 0.002785515320334262, "graph_miss_rate": 0.6601671309192201, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.6573816155988857, "padded_tokens_per_useful_token": 0.0003083555714376286, "padding_fraction": 0.07853787433940106 } }, "P04-C00-moderate": { "blocks": [ { "bucket": 1456.0, "duration_ms": 8981.908387999994, "eligible_miss": 0.0, "miss": 4.0, "model": 186.0, "overflow": 4.0, "padding": 0.0, "tokens": 33537.0 }, { "bucket": 2618.0, "duration_ms": 10098.805099999992, "eligible_miss": 0.0, "miss": 3.0, "model": 332.0, "overflow": 3.0, "padding": 7.0, "tokens": 24601.0 }, { "bucket": 1840.0, "duration_ms": 9484.212540999995, "eligible_miss": 0.0, "miss": 4.0, "model": 234.0, "overflow": 4.0, "padding": 0.0, "tokens": 29683.0 }, { "bucket": 2231.0, "duration_ms": 9981.909945, "eligible_miss": 0.0, "miss": 4.0, "model": 285.0, "overflow": 4.0, "padding": 6.0, "tokens": 33276.0 }, { "bucket": 1936.0, "duration_ms": 8581.831738000003, "eligible_miss": 0.0, "miss": 3.0, "model": 245.0, "overflow": 3.0, "padding": 0.0, "tokens": 19888.0 }, { "bucket": 2135.0, "duration_ms": 10071.43481000001, "eligible_miss": 0.0, "miss": 4.0, "model": 273.0, "overflow": 4.0, "padding": 6.0, "tokens": 34368.0 }, { "bucket": 1408.0, "duration_ms": 8588.356751000007, "eligible_miss": 0.0, "miss": 4.0, "model": 180.0, "overflow": 4.0, "padding": 0.0, "tokens": 27431.0 }, { "bucket": 2368.0, "duration_ms": 11072.200314999998, "eligible_miss": 0.0, "miss": 4.0, "model": 300.0, "overflow": 4.0, "padding": 0.0, "tokens": 35136.0 }, { "bucket": 2552.0, "duration_ms": 8904.710039000003, "eligible_miss": 0.0, "miss": 2.0, "model": 288.0, "overflow": 2.0, "padding": 28.0, "tokens": 16184.0 }, { "bucket": 1786.0, "duration_ms": 8996.101777999997, "eligible_miss": 0.0, "miss": 5.0, "model": 230.0, "overflow": 5.0, "padding": 4.0, "tokens": 38785.0 }, { "bucket": 3208.0, "duration_ms": 8631.933416999998, "eligible_miss": 0.0, "miss": 1.0, "model": 341.0, "overflow": 1.0, "padding": 6.0, "tokens": 11394.0 }, { "bucket": 1359.0, "duration_ms": 7128.594627000001, "eligible_miss": 0.0, "miss": 4.0, "model": 176.0, "overflow": 4.0, "padding": 6.0, "tokens": 33353.0 }, { "bucket": 2200.0, "duration_ms": 9367.741511, "eligible_miss": 0.0, "miss": 3.0, "model": 278.0, "overflow": 3.0, "padding": 0.0, "tokens": 23940.0 }, { "bucket": 1874.0, "duration_ms": 9525.214446999997, "eligible_miss": 0.0, "miss": 5.0, "model": 241.0, "overflow": 5.0, "padding": 7.0, "tokens": 40863.0 }, { "bucket": 2824.0, "duration_ms": 8884.210989, "eligible_miss": 0.0, "miss": 1.0, "model": 323.0, "overflow": 1.0, "padding": 3.0, "tokens": 11013.0 }, { "bucket": 1503.0, "duration_ms": 8559.785575, "eligible_miss": 0.0, "miss": 5.0, "model": 195.0, "overflow": 5.0, "padding": 7.0, "tokens": 40929.0 }, { "bucket": 2776.0, "duration_ms": 9198.640848000005, "eligible_miss": 0.0, "miss": 1.0, "model": 348.0, "overflow": 1.0, "padding": 0.0, "tokens": 8403.0 }, { "bucket": 1297.0, "duration_ms": 8906.830054, "eligible_miss": 0.0, "miss": 6.0, "model": 170.0, "overflow": 6.0, "padding": 4.0, "tokens": 46993.0 }, { "bucket": 3064.0, "duration_ms": 8544.142515999998, "eligible_miss": 0.0, "miss": 0.0, "model": 383.0, "overflow": 0.0, "padding": 0.0, "tokens": 3064.0 }, { "bucket": 1010.0, "duration_ms": 7998.338001000001, "eligible_miss": 0.0, "miss": 6.0, "model": 134.0, "overflow": 6.0, "padding": 4.0, "tokens": 47062.0 }, { "bucket": 2744.0, "duration_ms": 8611.122775000005, "eligible_miss": 0.0, "miss": 1.0, "model": 344.0, "overflow": 1.0, "padding": 0.0, "tokens": 7439.0 }, { "bucket": 1327.0, "duration_ms": 9267.594286, "eligible_miss": 0.0, "miss": 6.0, "model": 174.0, "overflow": 6.0, "padding": 6.0, "tokens": 50473.0 }, { "bucket": 2840.0, "duration_ms": 8589.381527999998, "eligible_miss": 0.0, "miss": 1.0, "model": 356.0, "overflow": 1.0, "padding": 0.0, "tokens": 4600.0 }, { "bucket": 1231.0, "duration_ms": 8726.466514, "eligible_miss": 0.0, "miss": 6.0, "model": 162.0, "overflow": 6.0, "padding": 7.0, "tokens": 47914.0 }, { "bucket": 3056.0, "duration_ms": 9110.523627999997, "eligible_miss": 0.0, "miss": 1.0, "model": 383.0, "overflow": 1.0, "padding": 0.0, "tokens": 4266.0 }, { "bucket": 1015.0, "duration_ms": 8217.807083000002, "eligible_miss": 0.0, "miss": 6.0, "model": 135.0, "overflow": 6.0, "padding": 6.0, "tokens": 47537.0 }, { "bucket": 3192.0, "duration_ms": 9264.992175999996, "eligible_miss": 0.0, "miss": 0.0, "model": 399.0, "overflow": 0.0, "padding": 0.0, "tokens": 3192.0 }, { "bucket": 882.0, "duration_ms": 8246.404675000002, "eligible_miss": 0.0, "miss": 6.0, "model": 118.0, "overflow": 6.0, "padding": 4.0, "tokens": 50030.0 }, { "bucket": 2768.0, "duration_ms": 9175.787352999994, "eligible_miss": 0.0, "miss": 1.0, "model": 347.0, "overflow": 1.0, "padding": 0.0, "tokens": 7379.0 }, { "bucket": 1311.0, "duration_ms": 9409.615027000003, "eligible_miss": 0.0, "miss": 6.0, "model": 172.0, "overflow": 6.0, "padding": 6.0, "tokens": 46846.0 }, { "bucket": 3352.0, "duration_ms": 9545.358950999997, "eligible_miss": 0.0, "miss": 0.0, "model": 419.0, "overflow": 0.0, "padding": 0.0, "tokens": 3352.0 }, { "bucket": 721.0, "duration_ms": 7947.838777999999, "eligible_miss": 0.0, "miss": 6.0, "model": 98.0, "overflow": 6.0, "padding": 4.0, "tokens": 48373.0 }, { "bucket": 3400.0, "duration_ms": 9494.459786, "eligible_miss": 0.0, "miss": 0.0, "model": 425.0, "overflow": 0.0, "padding": 0.0, "tokens": 3400.0 }, { "bucket": 666.0, "duration_ms": 7796.334624, "eligible_miss": 0.0, "miss": 7.0, "model": 92.0, "overflow": 7.0, "padding": 4.0, "tokens": 50886.0 }, { "bucket": 3264.0, "duration_ms": 9631.711120000004, "eligible_miss": 0.0, "miss": 0.0, "model": 408.0, "overflow": 0.0, "padding": 0.0, "tokens": 3264.0 }, { "bucket": 815.0, "duration_ms": 8377.705931, "eligible_miss": 0.0, "miss": 6.0, "model": 110.0, "overflow": 6.0, "padding": 6.0, "tokens": 49358.0 }, { "bucket": 3800.0, "duration_ms": 9837.149042000003, "eligible_miss": 0.0, "miss": 0.0, "model": 475.0, "overflow": 0.0, "padding": 0.0, "tokens": 3800.0 }, { "bucket": 374.0, "duration_ms": 6803.713179000001, "eligible_miss": 0.0, "miss": 6.0, "model": 54.0, "overflow": 6.0, "padding": 7.0, "tokens": 47662.0 }, { "bucket": 3304.0, "duration_ms": 9963.765209000001, "eligible_miss": 0.0, "miss": 0.0, "model": 413.0, "overflow": 0.0, "padding": 0.0, "tokens": 3304.0 }, { "bucket": 673.0, "duration_ms": 8837.429310000001, "eligible_miss": 0.0, "miss": 7.0, "model": 93.0, "overflow": 7.0, "padding": 4.0, "tokens": 54138.0 }, { "bucket": 3560.0, "duration_ms": 9562.608677000004, "eligible_miss": 0.0, "miss": 0.0, "model": 445.0, "overflow": 0.0, "padding": 0.0, "tokens": 3560.0 }, { "bucket": 946.0, "duration_ms": 8044.274325999995, "eligible_miss": 0.0, "miss": 6.0, "model": 126.0, "overflow": 6.0, "padding": 7.0, "tokens": 45628.0 }, { "bucket": 3631.0, "duration_ms": 9953.335582999998, "eligible_miss": 0.0, "miss": 0.0, "model": 456.0, "overflow": 0.0, "padding": 3.0, "tokens": 3628.0 }, { "bucket": 232.0, "duration_ms": 6868.462794000001, "eligible_miss": 0.0, "miss": 7.0, "model": 36.0, "overflow": 7.0, "padding": 0.0, "tokens": 49763.0 }, { "bucket": 3640.0, "duration_ms": 9983.985477999997, "eligible_miss": 0.0, "miss": 0.0, "model": 455.0, "overflow": 0.0, "padding": 0.0, "tokens": 3640.0 }, { "bucket": 449.0, "duration_ms": 7694.749212000002, "eligible_miss": 0.0, "miss": 7.0, "model": 65.0, "overflow": 7.0, "padding": 7.0, "tokens": 51796.0 }, { "bucket": 3760.0, "duration_ms": 9970.747046999993, "eligible_miss": 0.0, "miss": 0.0, "model": 470.0, "overflow": 0.0, "padding": 0.0, "tokens": 3760.0 }, { "bucket": 591.0, "duration_ms": 7556.453625000001, "eligible_miss": 0.0, "miss": 7.0, "model": 83.0, "overflow": 7.0, "padding": 6.0, "tokens": 48512.0 } ], "clean": { "admitted": 192, "completed": 192, "completed_throughput_rps": 0.8, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 1184043, "offered_rps": 0.8, "output_tokens": 98304, "start_s": 60.0 }, "config": "C00", "drain_quarantined": false, "drain_seconds": 1.4950859160162508, "latency_s": { "e2e": { "mean": 8.979008184640861, "n": 192, "p50": 8.750423648001743, "p95": 9.690806861204328, "p99": 13.313055781236617 }, "tpot": { "mean": 0.013778383638832437, "n": 192, "p50": 0.013384224433496772, "p95": 0.01721187468572363, "p99": 0.023013204993655518 }, "ttft": { "mean": 1.9382541451974855, "n": 192, "p50": 2.007326473496505, "p95": 3.2427438382524993, "p99": 3.608097693949822 } }, "layer1": { "decode_tokens": 98661, "kv_usage_max": 0.36836982968369825, "kv_usage_mean": 0.17221124824207087, "mode_counts": { "FULL": 12291, "NONE": 208, "PIECEWISE": 2 }, "mode_shares": { "FULL": 0.9832013438924886, "NONE": 0.01663866890648748, "PIECEWISE": 0.00015998720102391808 }, "preemptions": 0, "prefill_tokens": 1208742, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 6, "queue_waiting_mean": 0.024478041756659467, "records_all": 19184, "records_clean": 12501, "requests_per_step": { "mean": 7.917766578673706, "n": 12501, "p50": 8.0, "p95": 8.0, "p99": 8.0 }, "scheduled_tokens_per_step": { "mean": 104.5838732901368, "n": 12501, "p50": 8.0, "p95": 8.0, "p99": 7505.0 }, "step_duration_ms": { "mean": 34.23699552891769, "n": 12501, "p50": 22.373712, "p95": 25.211079, "p99": 784.700082 }, "token_efficiency_per_ms": 3.0547035940055496 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P04", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 0.8, "clean_c_waiting_median": 0.0, "completion_rate_rps": 0.8, "completion_rate_within_10pct": true, "tail_end_s": 331.31545102299424, "tail_start_s": 321.31545102299424, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 0.8, "clean_c_waiting_median": 0.0, "completion_rate_rps": 0.8, "completion_rate_within_10pct": true, "tail_end_s": 362.91449153699796, "tail_start_s": 352.91449153699796, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": true, "requests_completed": 192, "run_dir": "runs/phase3/primary/P04-C00/moderate", "run_id": "P04-C00-moderate", "trace_files": 2, "waste": { "R128": 0.24734040984998104, "R32": 0.23857870988687485, "R64": 0.24443376797326863, "bucket_slack": 0.00166685187243027, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.013006824568446406, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 141, "moe_layer_cv": null, "overflow_rate": 0.013006824568446406, "padded_tokens_per_useful_token": 0.00012620439145389755, "padding_fraction": 0.00166685187243027 } }, "P04-C00-saturation": { "blocks": [ { "bucket": 7760.0, "duration_ms": 9661.424796000003, "eligible_miss": 0.0, "miss": 0.0, "model": 156.0, "overflow": 0.0, "padding": 664.0, "tokens": 7096.0 }, { "bucket": 4560.0, "duration_ms": 11026.035121000004, "eligible_miss": 0.0, "miss": 6.0, "model": 101.0, "overflow": 6.0, "padding": 476.0, "tokens": 41799.0 }, { "duration_ms": 10369.803374000001, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81920.0 }, { "duration_ms": 9400.000758999999, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "duration_ms": 10727.988309, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81920.0 }, { "bucket": 5280.0, "duration_ms": 8557.027166000002, "eligible_miss": 0.0, "miss": 3.0, "model": 113.0, "overflow": 3.0, "padding": 21.0, "tokens": 16948.0 }, { "bucket": 8112.0, "duration_ms": 9916.120584999993, "eligible_miss": 0.0, "miss": 0.0, "model": 169.0, "overflow": 0.0, "padding": 231.0, "tokens": 7881.0 }, { "bucket": 7920.0, "duration_ms": 9986.177872999995, "eligible_miss": 0.0, "miss": 0.0, "model": 165.0, "overflow": 0.0, "padding": 436.0, "tokens": 7484.0 }, { "bucket": 1488.0, "duration_ms": 11304.550902000003, "eligible_miss": 0.0, "miss": 11.0, "model": 42.0, "overflow": 11.0, "padding": 94.0, "tokens": 74374.0 }, { "duration_ms": 9583.59484, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "duration_ms": 9862.853266, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "bucket": 48.0, "duration_ms": 10026.114451, "eligible_miss": 0.0, "miss": 9.0, "model": 10.0, "overflow": 9.0, "padding": 0.0, "tokens": 73216.0 }, { "bucket": 7152.0, "duration_ms": 9198.616807000002, "eligible_miss": 0.0, "miss": 1.0, "model": 150.0, "overflow": 1.0, "padding": 109.0, "tokens": 11483.0 }, { "bucket": 7968.0, "duration_ms": 9991.270598000001, "eligible_miss": 0.0, "miss": 1.0, "model": 167.0, "overflow": 1.0, "padding": 294.0, "tokens": 11577.0 }, { "bucket": 7632.0, "duration_ms": 10544.012887999994, "eligible_miss": 0.0, "miss": 2.0, "model": 161.0, "overflow": 2.0, "padding": 512.0, "tokens": 18576.0 }, { "duration_ms": 9973.108670000001, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 76425.0 }, { "duration_ms": 10665.678355, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81920.0 }, { "duration_ms": 9722.500454999998, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "bucket": 1984.0, "duration_ms": 9096.570938999997, "eligible_miss": 0.0, "miss": 6.0, "model": 40.0, "overflow": 6.0, "padding": 49.0, "tokens": 50598.0 }, { "bucket": 7872.0, "duration_ms": 9917.962257000005, "eligible_miss": 0.0, "miss": 0.0, "model": 164.0, "overflow": 0.0, "padding": 250.0, "tokens": 7622.0 }, { "bucket": 7440.0, "duration_ms": 10042.182822000002, "eligible_miss": 0.0, "miss": 1.0, "model": 156.0, "overflow": 1.0, "padding": 382.0, "tokens": 9371.0 }, { "bucket": 5856.0, "duration_ms": 10961.045746999998, "eligible_miss": 0.0, "miss": 5.0, "model": 127.0, "overflow": 5.0, "padding": 428.0, "tokens": 32912.0 }, { "duration_ms": 9701.789703, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 73342.0 }, { "duration_ms": 10480.6525, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81920.0 }, { "duration_ms": 9541.685850000002, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "bucket": 4008.0, "duration_ms": 9259.903107000004, "eligible_miss": 0.0, "miss": 4.0, "model": 79.0, "overflow": 4.0, "padding": 357.0, "tokens": 36411.0 }, { "bucket": 8016.0, "duration_ms": 9968.672883000003, "eligible_miss": 0.0, "miss": 1.0, "model": 168.0, "overflow": 1.0, "padding": 39.0, "tokens": 10814.0 }, { "bucket": 7728.0, "duration_ms": 10029.055906999994, "eligible_miss": 0.0, "miss": 1.0, "model": 162.0, "overflow": 1.0, "padding": 232.0, "tokens": 10443.0 }, { "bucket": 3504.0, "duration_ms": 11264.764591, "eligible_miss": 0.0, "miss": 8.0, "model": 81.0, "overflow": 8.0, "padding": 149.0, "tokens": 61248.0 }, { "duration_ms": 10113.265851999999, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 78314.0 }, { "duration_ms": 9743.199005, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "duration_ms": 9638.610864000002, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "bucket": 6288.0, "duration_ms": 9178.285882, "eligible_miss": 0.0, "miss": 2.0, "model": 133.0, "overflow": 2.0, "padding": 16.0, "tokens": 13431.0 }, { "bucket": 8064.0, "duration_ms": 10005.450483999997, "eligible_miss": 0.0, "miss": 0.0, "model": 168.0, "overflow": 0.0, "padding": 226.0, "tokens": 7838.0 }, { "bucket": 7296.0, "duration_ms": 10016.172216999998, "eligible_miss": 0.0, "miss": 1.0, "model": 153.0, "overflow": 1.0, "padding": 377.0, "tokens": 10862.0 }, { "bucket": 1152.0, "duration_ms": 10843.782151, "eligible_miss": 0.0, "miss": 10.0, "model": 34.0, "overflow": 10.0, "padding": 73.0, "tokens": 75324.0 }, { "duration_ms": 10150.313138, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 76025.0 }, { "duration_ms": 9713.204290000001, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "bucket": 624.0, "duration_ms": 9239.420065000002, "eligible_miss": 0.0, "miss": 8.0, "model": 21.0, "overflow": 8.0, "padding": 0.0, "tokens": 63071.0 }, { "bucket": 8112.0, "duration_ms": 10021.796982, "eligible_miss": 0.0, "miss": 1.0, "model": 170.0, "overflow": 1.0, "padding": 46.0, "tokens": 10196.0 }, { "bucket": 8208.0, "duration_ms": 9994.886259000003, "eligible_miss": 0.0, "miss": 0.0, "model": 171.0, "overflow": 0.0, "padding": 222.0, "tokens": 7986.0 }, { "bucket": 5904.0, "duration_ms": 11039.833101999997, "eligible_miss": 0.0, "miss": 5.0, "model": 128.0, "overflow": 5.0, "padding": 284.0, "tokens": 35573.0 }, { "duration_ms": 9913.298117, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "duration_ms": 9716.298324, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "duration_ms": 10405.118951999999, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81920.0 }, { "bucket": 3216.0, "duration_ms": 8902.433363000002, "eligible_miss": 0.0, "miss": 4.0, "model": 71.0, "overflow": 4.0, "padding": 67.0, "tokens": 35679.0 }, { "bucket": 7296.0, "duration_ms": 9963.001459999998, "eligible_miss": 0.0, "miss": 1.0, "model": 153.0, "overflow": 1.0, "padding": 282.0, "tokens": 11615.0 }, { "bucket": 7728.0, "duration_ms": 10025.764016999992, "eligible_miss": 0.0, "miss": 0.0, "model": 161.0, "overflow": 0.0, "padding": 480.0, "tokens": 7248.0 } ], "clean": { "admitted": 324, "completed": 324, "completed_throughput_rps": 1.35, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 1969814, "offered_rps": 1.35, "output_tokens": 165888, "start_s": 60.0 }, "config": "C00", "drain_quarantined": false, "drain_seconds": 168.52608891300042, "latency_s": { "e2e": { "mean": 153.5840079071512, "n": 324, "p50": 176.7334543744946, "p95": 204.46718762134697, "p99": 209.50116568645083 }, "tpot": { "mean": 0.06281919152370617, "n": 324, "p50": 0.06188693252445537, "p95": 0.06422231276379772, "p99": 0.08522842260954068 }, "ttft": { "mean": 121.48340103853735, "n": 324, "p50": 145.04611464199843, "p95": 173.27588533475497, "p99": 178.38239817070252 } }, "layer1": { "decode_tokens": 252604, "kv_usage_max": 1.0, "kv_usage_mean": 0.9870783228921769, "mode_counts": { "FULL": 3481, "NONE": 272, "PIECEWISE": 2 }, "mode_shares": { "FULL": 0.9270306258322237, "NONE": 0.07243675099866845, "PIECEWISE": 0.0005326231691078562 }, "preemptions": 24, "prefill_tokens": 1967058, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 213, "queue_waiting_mean": 209.8069241011984, "records_all": 8254, "records_clean": 3755, "requests_per_step": { "mean": 46.02103861517976, "n": 3755, "p50": 46.0, "p95": 48.0, "p99": 49.0 }, "scheduled_tokens_per_step": { "mean": 591.1217043941411, "n": 3755, "p50": 46.0, "p95": 8192.0, "p99": 8192.0 }, "step_duration_ms": { "mean": 127.6711850985353, "n": 3755, "p50": 59.800215, "p95": 1020.3509887999998, "p99": 1101.04686276 }, "token_efficiency_per_ms": 4.630032249938932 }, "layer2_missing_after_controller_cleanup": false, "load": "saturation", "pattern": "P04", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 1.15, "clean_c_waiting_median": 210.0, "completion_rate_rps": 0.1, "completion_rate_within_10pct": false, "tail_end_s": 333.2067631710088, "tail_start_s": 323.2067631710088, "valid": false, "waiting_median": 212.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 1.15, "clean_c_waiting_median": 210.0, "completion_rate_rps": 0.7, "completion_rate_within_10pct": false, "tail_end_s": 366.1246157819987, "tail_start_s": 356.1246157819987, "valid": false, "waiting_median": 209.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 324, "run_dir": "runs/phase3/primary/P04-C00/saturation", "run_id": "P04-C00-saturation", "trace_files": 2, "waste": { "R128": 0.24734040984998104, "R32": 0.23857870988687485, "R64": 0.24443376797326863, "bucket_slack": 0.04040043753269606, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.07243675099866845, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.07243675099866845, "padded_tokens_per_useful_token": 0.0030617274161561536, "padding_fraction": 0.04040043753269606 } }, "P06-C00-moderate": { "blocks": [ { "bucket": 2896.0, "duration_ms": 9977.739791, "eligible_miss": 0.0, "miss": 5.0, "model": 318.0, "overflow": 5.0, "padding": 0.0, "tokens": 33597.0 }, { "bucket": 2656.0, "duration_ms": 10026.279938000003, "eligible_miss": 0.0, "miss": 4.0, "model": 326.0, "overflow": 4.0, "padding": 7.0, "tokens": 32460.0 }, { "bucket": 3832.0, "duration_ms": 9938.875863000001, "eligible_miss": 0.0, "miss": 2.0, "model": 322.0, "overflow": 2.0, "padding": 15.0, "tokens": 19113.0 }, { "bucket": 5096.0, "duration_ms": 11421.808803999997, "eligible_miss": 0.0, "miss": 3.0, "model": 395.0, "overflow": 3.0, "padding": 27.0, "tokens": 27356.0 }, { "bucket": 4112.0, "duration_ms": 8522.299042999995, "eligible_miss": 0.0, "miss": 0.0, "model": 421.0, "overflow": 0.0, "padding": 2.0, "tokens": 4110.0 }, { "bucket": 3264.0, "duration_ms": 9974.524448999991, "eligible_miss": 0.0, "miss": 3.0, "model": 336.0, "overflow": 3.0, "padding": 12.0, "tokens": 26847.0 }, { "bucket": 3472.0, "duration_ms": 9979.503383000014, "eligible_miss": 0.0, "miss": 4.0, "model": 329.0, "overflow": 4.0, "padding": 7.0, "tokens": 28440.0 }, { "bucket": 3376.0, "duration_ms": 9994.057406999997, "eligible_miss": 0.0, "miss": 4.0, "model": 330.0, "overflow": 4.0, "padding": 10.0, "tokens": 29265.0 }, { "bucket": 3680.0, "duration_ms": 9988.828849000003, "eligible_miss": 0.0, "miss": 3.0, "model": 335.0, "overflow": 3.0, "padding": 0.0, "tokens": 20268.0 }, { "bucket": 3288.0, "duration_ms": 9975.919217, "eligible_miss": 0.0, "miss": 3.0, "model": 336.0, "overflow": 3.0, "padding": 11.0, "tokens": 24992.0 }, { "bucket": 4632.0, "duration_ms": 9973.066123999999, "eligible_miss": 0.0, "miss": 1.0, "model": 440.0, "overflow": 1.0, "padding": 7.0, "tokens": 12364.0 }, { "bucket": 3712.0, "duration_ms": 9796.098216, "eligible_miss": 0.0, "miss": 3.0, "model": 422.0, "overflow": 3.0, "padding": 17.0, "tokens": 28271.0 }, { "bucket": 3520.0, "duration_ms": 10179.04618099999, "eligible_miss": 0.0, "miss": 3.0, "model": 410.0, "overflow": 3.0, "padding": 14.0, "tokens": 28082.0 }, { "bucket": 3296.0, "duration_ms": 8780.04112, "eligible_miss": 0.0, "miss": 2.0, "model": 313.0, "overflow": 2.0, "padding": 20.0, "tokens": 13630.0 }, { "bucket": 3184.0, "duration_ms": 9968.883369999992, "eligible_miss": 0.0, "miss": 5.0, "model": 259.0, "overflow": 5.0, "padding": 11.0, "tokens": 32334.0 }, { "bucket": 4288.0, "duration_ms": 9980.859213000005, "eligible_miss": 0.0, "miss": 2.0, "model": 348.0, "overflow": 2.0, "padding": 17.0, "tokens": 17762.0 }, { "bucket": 3952.0, "duration_ms": 9992.083239999998, "eligible_miss": 0.0, "miss": 3.0, "model": 348.0, "overflow": 3.0, "padding": 9.0, "tokens": 22666.0 }, { "bucket": 3688.0, "duration_ms": 9978.982320999996, "eligible_miss": 0.0, "miss": 3.0, "model": 380.0, "overflow": 3.0, "padding": 11.0, "tokens": 21289.0 }, { "bucket": 2592.0, "duration_ms": 10035.271873999998, "eligible_miss": 0.0, "miss": 5.0, "model": 328.0, "overflow": 5.0, "padding": 0.0, "tokens": 30630.0 }, { "bucket": 3576.0, "duration_ms": 11149.077350000001, "eligible_miss": 0.0, "miss": 4.0, "model": 382.0, "overflow": 4.0, "padding": 6.0, "tokens": 36338.0 }, { "bucket": 3136.0, "duration_ms": 9374.885931000008, "eligible_miss": 0.0, "miss": 4.0, "model": 269.0, "overflow": 4.0, "padding": 15.0, "tokens": 23355.0 }, { "bucket": 4768.0, "duration_ms": 9343.843769999994, "eligible_miss": 0.0, "miss": 0.0, "model": 353.0, "overflow": 0.0, "padding": 15.0, "tokens": 4753.0 }, { "bucket": 4016.0, "duration_ms": 9988.893537000016, "eligible_miss": 0.0, "miss": 3.0, "model": 318.0, "overflow": 3.0, "padding": 20.0, "tokens": 28572.0 }, { "bucket": 3768.0, "duration_ms": 9978.159868, "eligible_miss": 0.0, "miss": 4.0, "model": 349.0, "overflow": 4.0, "padding": 13.0, "tokens": 25966.0 }, { "bucket": 3848.0, "duration_ms": 9978.960759999996, "eligible_miss": 0.0, "miss": 3.0, "model": 399.0, "overflow": 3.0, "padding": 13.0, "tokens": 22342.0 }, { "bucket": 3648.0, "duration_ms": 9980.344796999996, "eligible_miss": 0.0, "miss": 3.0, "model": 424.0, "overflow": 3.0, "padding": 8.0, "tokens": 19594.0 }, { "bucket": 3544.0, "duration_ms": 9970.853603000001, "eligible_miss": 0.0, "miss": 3.0, "model": 363.0, "overflow": 3.0, "padding": 6.0, "tokens": 26235.0 }, { "bucket": 3280.0, "duration_ms": 10198.273267000004, "eligible_miss": 0.0, "miss": 3.0, "model": 359.0, "overflow": 3.0, "padding": 0.0, "tokens": 27480.0 }, { "bucket": 4040.0, "duration_ms": 10590.225440999997, "eligible_miss": 0.0, "miss": 3.0, "model": 407.0, "overflow": 3.0, "padding": 11.0, "tokens": 26086.0 }, { "bucket": 4384.0, "duration_ms": 10426.231084000008, "eligible_miss": 0.0, "miss": 2.0, "model": 447.0, "overflow": 2.0, "padding": 6.0, "tokens": 20762.0 }, { "bucket": 3056.0, "duration_ms": 8686.102160000002, "eligible_miss": 0.0, "miss": 2.0, "model": 322.0, "overflow": 2.0, "padding": 6.0, "tokens": 15162.0 }, { "bucket": 4816.0, "duration_ms": 9979.046929000002, "eligible_miss": 0.0, "miss": 2.0, "model": 434.0, "overflow": 2.0, "padding": 22.0, "tokens": 15088.0 }, { "bucket": 2752.0, "duration_ms": 9979.596705000002, "eligible_miss": 0.0, "miss": 4.0, "model": 348.0, "overflow": 4.0, "padding": 0.0, "tokens": 32405.0 }, { "bucket": 3696.0, "duration_ms": 9974.602910999998, "eligible_miss": 0.0, "miss": 4.0, "model": 370.0, "overflow": 4.0, "padding": 11.0, "tokens": 24107.0 }, { "bucket": 4248.0, "duration_ms": 9966.603755999997, "eligible_miss": 0.0, "miss": 2.0, "model": 454.0, "overflow": 2.0, "padding": 18.0, "tokens": 13044.0 }, { "bucket": 3100.0, "duration_ms": 8939.906178000005, "eligible_miss": 0.0, "miss": 3.0, "model": 391.0, "overflow": 3.0, "padding": 1.0, "tokens": 22061.0 }, { "bucket": 3416.0, "duration_ms": 11407.424273999997, "eligible_miss": 0.0, "miss": 4.0, "model": 431.0, "overflow": 4.0, "padding": 0.0, "tokens": 35009.0 }, { "bucket": 3016.0, "duration_ms": 9221.427410000006, "eligible_miss": 0.0, "miss": 4.0, "model": 360.0, "overflow": 4.0, "padding": 8.0, "tokens": 18203.0 }, { "bucket": 4488.0, "duration_ms": 9300.330514999992, "eligible_miss": 0.0, "miss": 0.0, "model": 409.0, "overflow": 0.0, "padding": 12.0, "tokens": 4476.0 }, { "bucket": 3168.0, "duration_ms": 9992.190109000017, "eligible_miss": 0.0, "miss": 3.0, "model": 336.0, "overflow": 3.0, "padding": 10.0, "tokens": 26458.0 }, { "bucket": 2896.0, "duration_ms": 9985.548586999997, "eligible_miss": 0.0, "miss": 5.0, "model": 254.0, "overflow": 5.0, "padding": 7.0, "tokens": 34100.0 }, { "bucket": 3408.0, "duration_ms": 9982.407799000004, "eligible_miss": 0.0, "miss": 4.0, "model": 304.0, "overflow": 4.0, "padding": 0.0, "tokens": 28456.0 }, { "bucket": 3640.0, "duration_ms": 9981.351961999993, "eligible_miss": 0.0, "miss": 4.0, "model": 318.0, "overflow": 4.0, "padding": 18.0, "tokens": 28462.0 }, { "bucket": 4400.0, "duration_ms": 9964.023838000003, "eligible_miss": 0.0, "miss": 3.0, "model": 405.0, "overflow": 3.0, "padding": 14.0, "tokens": 21380.0 }, { "bucket": 3552.0, "duration_ms": 10730.976689999996, "eligible_miss": 0.0, "miss": 4.0, "model": 429.0, "overflow": 4.0, "padding": 9.0, "tokens": 31431.0 }, { "bucket": 3352.0, "duration_ms": 10643.849985000004, "eligible_miss": 0.0, "miss": 4.0, "model": 422.0, "overflow": 4.0, "padding": 7.0, "tokens": 28467.0 }, { "bucket": 3272.0, "duration_ms": 8558.336599999995, "eligible_miss": 0.0, "miss": 1.0, "model": 322.0, "overflow": 1.0, "padding": 11.0, "tokens": 11404.0 }, { "bucket": 4920.0, "duration_ms": 9976.434318000003, "eligible_miss": 0.0, "miss": 2.0, "model": 389.0, "overflow": 2.0, "padding": 21.0, "tokens": 18903.0 } ], "clean": { "admitted": 336, "completed": 336, "completed_throughput_rps": 1.4, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 955216, "offered_rps": 1.4, "output_tokens": 172032, "start_s": 60.0 }, "config": "C00", "drain_quarantined": false, "drain_seconds": 5.683892283006571, "latency_s": { "e2e": { "mean": 8.300746099748721, "n": 336, "p50": 8.40417995498865, "p95": 9.786131062501227, "p99": 10.154464515444124 }, "tpot": { "mean": 0.01437395923223587, "n": 336, "p50": 0.01442530346280711, "p95": 0.017416477798915524, "p99": 0.018449774422510133 }, "ttft": { "mean": 0.9556529320761911, "n": 336, "p50": 0.9955719049903564, "p95": 1.8687072527463897, "p99": 2.1914087791024928 } }, "layer1": { "decode_tokens": 173276, "kv_usage_max": 0.23579345769126792, "kv_usage_mean": 0.10409258767106862, "mode_counts": { "FULL": 17310, "NONE": 149, "PIECEWISE": 9 }, "mode_shares": { "FULL": 0.9909548889397756, "NONE": 0.008529883215021754, "PIECEWISE": 0.0005152278452026563 }, "preemptions": 0, "prefill_tokens": 950299, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 6, "queue_waiting_mean": 0.011735745362949393, "records_all": 25870, "records_clean": 17468, "requests_per_step": { "mean": 9.943782917334554, "n": 17468, "p50": 8.0, "p95": 16.0, "p99": 16.0 }, "scheduled_tokens_per_step": { "mean": 64.32190290817495, "n": 17468, "p50": 8.0, "p95": 16.0, "p99": 16.0 }, "step_duration_ms": { "mean": 27.291852446588045, "n": 17468, "p50": 19.243071, "p95": 28.63492535, "p99": 93.35969100999505 }, "token_efficiency_per_ms": 2.3568170403257582 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P06", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 1.6, "clean_c_waiting_median": 0.0, "completion_rate_rps": 0.8, "completion_rate_within_10pct": false, "tail_end_s": 331.6668705250195, "tail_start_s": 321.6668705250195, "valid": false, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 1.6, "clean_c_waiting_median": 0.0, "completion_rate_rps": 1.6, "completion_rate_within_10pct": true, "tail_end_s": 363.2625439830008, "tail_start_s": 353.2625439830008, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 336, "run_dir": "runs/phase3/primary/P06-C00/moderate", "run_id": "P06-C00-moderate", "trace_files": 2, "waste": { "R128": 0.6023504575478206, "R32": 0.5930739622699981, "R64": 0.5988308514107739, "bucket_slack": 0.002759758734494139, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.008302794319743472, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 152, "moe_layer_cv": null, "overflow_rate": 0.008302794319743472, "padded_tokens_per_useful_token": 0.00043165787775626904, "padding_fraction": 0.002759758734494139 } }, "P06-C00-saturation": { "blocks": [ { "bucket": 12200.0, "duration_ms": 9955.488134000001, "eligible_miss": 0.0, "miss": 1.0, "model": 119.0, "overflow": 1.0, "padding": 685.0, "tokens": 15219.0 }, { "bucket": 11712.0, "duration_ms": 9996.430858999998, "eligible_miss": 0.0, "miss": 2.0, "model": 124.0, "overflow": 2.0, "padding": 346.0, "tokens": 16607.0 }, { "bucket": 12288.0, "duration_ms": 10013.737815999999, "eligible_miss": 0.0, "miss": 1.0, "model": 129.0, "overflow": 1.0, "padding": 673.0, "tokens": 13629.0 }, { "bucket": 368.0, "duration_ms": 10611.232619999999, "eligible_miss": 0.0, "miss": 11.0, "model": 15.0, "overflow": 11.0, "padding": 15.0, "tokens": 84440.0 }, { "duration_ms": 10559.656503, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81920.0 }, { "duration_ms": 9437.028964000001, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "bucket": 2184.0, "duration_ms": 9372.165505999996, "eligible_miss": 0.0, "miss": 7.0, "model": 28.0, "overflow": 7.0, "padding": 53.0, "tokens": 58674.0 }, { "bucket": 12896.0, "duration_ms": 9988.717321, "eligible_miss": 0.0, "miss": 0.0, "model": 124.0, "overflow": 0.0, "padding": 516.0, "tokens": 12380.0 }, { "bucket": 12104.0, "duration_ms": 9950.489277, "eligible_miss": 0.0, "miss": 1.0, "model": 122.0, "overflow": 1.0, "padding": 546.0, "tokens": 12471.0 }, { "bucket": 11904.0, "duration_ms": 10044.752167999994, "eligible_miss": 0.0, "miss": 0.0, "model": 124.0, "overflow": 0.0, "padding": 581.0, "tokens": 11323.0 }, { "bucket": 7856.0, "duration_ms": 11363.681751999999, "eligible_miss": 0.0, "miss": 6.0, "model": 92.0, "overflow": 6.0, "padding": 276.0, "tokens": 45842.0 }, { "duration_ms": 9348.223145, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "duration_ms": 10283.85525, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81920.0 }, { "duration_ms": 9479.791809, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "bucket": 7952.0, "duration_ms": 9480.092465, "eligible_miss": 0.0, "miss": 4.0, "model": 75.0, "overflow": 4.0, "padding": 305.0, "tokens": 34686.0 }, { "bucket": 13344.0, "duration_ms": 9951.624168, "eligible_miss": 0.0, "miss": 1.0, "model": 124.0, "overflow": 1.0, "padding": 523.0, "tokens": 15795.0 }, { "bucket": 13000.0, "duration_ms": 9992.023440000004, "eligible_miss": 0.0, "miss": 1.0, "model": 126.0, "overflow": 1.0, "padding": 431.0, "tokens": 15494.0 }, { "bucket": 12048.0, "duration_ms": 10005.716017999994, "eligible_miss": 0.0, "miss": 1.0, "model": 125.0, "overflow": 1.0, "padding": 237.0, "tokens": 18903.0 }, { "bucket": 3360.0, "duration_ms": 11177.442514, "eligible_miss": 0.0, "miss": 9.0, "model": 44.0, "overflow": 9.0, "padding": 104.0, "tokens": 73653.0 }, { "duration_ms": 9424.047387, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "duration_ms": 10728.534254, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81920.0 }, { "bucket": 480.0, "duration_ms": 9615.067625000001, "eligible_miss": 0.0, "miss": 9.0, "model": 14.0, "overflow": 9.0, "padding": 16.0, "tokens": 66217.0 }, { "bucket": 11328.0, "duration_ms": 9024.415422, "eligible_miss": 0.0, "miss": 0.0, "model": 118.0, "overflow": 0.0, "padding": 402.0, "tokens": 10926.0 }, { "bucket": 12272.0, "duration_ms": 10041.456662999999, "eligible_miss": 0.0, "miss": 0.0, "model": 132.0, "overflow": 0.0, "padding": 585.0, "tokens": 11687.0 }, { "bucket": 11792.0, "duration_ms": 9956.999717000004, "eligible_miss": 0.0, "miss": 0.0, "model": 134.0, "overflow": 0.0, "padding": 583.0, "tokens": 11209.0 }, { "bucket": 7824.0, "duration_ms": 10999.740231, "eligible_miss": 0.0, "miss": 5.0, "model": 94.0, "overflow": 5.0, "padding": 583.0, "tokens": 42306.0 }, { "duration_ms": 9748.006496000002, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "duration_ms": 10606.91422, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81920.0 }, { "duration_ms": 9383.162393, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "bucket": 7184.0, "duration_ms": 9217.577436, "eligible_miss": 0.0, "miss": 4.0, "model": 71.0, "overflow": 4.0, "padding": 189.0, "tokens": 35953.0 }, { "bucket": 12840.0, "duration_ms": 10052.109649000002, "eligible_miss": 0.0, "miss": 1.0, "model": 118.0, "overflow": 1.0, "padding": 421.0, "tokens": 20487.0 }, { "bucket": 11984.0, "duration_ms": 9913.599149, "eligible_miss": 0.0, "miss": 1.0, "model": 116.0, "overflow": 1.0, "padding": 209.0, "tokens": 19156.0 }, { "bucket": 12576.0, "duration_ms": 10053.582624999997, "eligible_miss": 0.0, "miss": 0.0, "model": 131.0, "overflow": 0.0, "padding": 493.0, "tokens": 12083.0 }, { "bucket": 4512.0, "duration_ms": 11061.520617999999, "eligible_miss": 0.0, "miss": 8.0, "model": 55.0, "overflow": 8.0, "padding": 252.0, "tokens": 63278.0 }, { "duration_ms": 9458.263235999999, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "duration_ms": 10419.149388, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81920.0 }, { "duration_ms": 9654.973689, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73553.0 }, { "bucket": 9592.0, "duration_ms": 9694.816922000002, "eligible_miss": 0.0, "miss": 2.0, "model": 111.0, "overflow": 2.0, "padding": 46.0, "tokens": 21082.0 }, { "bucket": 11352.0, "duration_ms": 9669.751934000002, "eligible_miss": 0.0, "miss": 0.0, "model": 129.0, "overflow": 0.0, "padding": 307.0, "tokens": 11045.0 }, { "bucket": 10912.0, "duration_ms": 9934.947404, "eligible_miss": 0.0, "miss": 1.0, "model": 127.0, "overflow": 1.0, "padding": 609.0, "tokens": 13237.0 }, { "bucket": 9040.0, "duration_ms": 10788.090522, "eligible_miss": 0.0, "miss": 4.0, "model": 117.0, "overflow": 4.0, "padding": 256.0, "tokens": 30161.0 }, { "duration_ms": 10598.505613999998, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81920.0 }, { "duration_ms": 9569.238599, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "duration_ms": 9677.49048, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "bucket": 4800.0, "duration_ms": 9392.868976999998, "eligible_miss": 0.0, "miss": 5.0, "model": 55.0, "overflow": 5.0, "padding": 76.0, "tokens": 44430.0 }, { "bucket": 11904.0, "duration_ms": 9982.797705000004, "eligible_miss": 0.0, "miss": 1.0, "model": 125.0, "overflow": 1.0, "padding": 396.0, "tokens": 16678.0 }, { "bucket": 12680.0, "duration_ms": 9975.084492000005, "eligible_miss": 0.0, "miss": 0.0, "model": 136.0, "overflow": 0.0, "padding": 467.0, "tokens": 12213.0 }, { "bucket": 10824.0, "duration_ms": 9999.780528000003, "eligible_miss": 0.0, "miss": 1.0, "model": 124.0, "overflow": 1.0, "padding": 107.0, "tokens": 18627.0 } ], "clean": { "admitted": 564, "completed": 564, "completed_throughput_rps": 2.35, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 1633038, "offered_rps": 2.35, "output_tokens": 288768, "start_s": 60.0 }, "config": "C00", "drain_quarantined": false, "drain_seconds": 95.17034762600088, "latency_s": { "e2e": { "mean": 101.44001434788701, "n": 564, "p50": 107.6167936980055, "p95": 122.415330010849, "p99": 126.31151792582939 }, "tpot": { "mean": 0.07128777578487226, "n": 564, "p50": 0.06864038345594425, "p95": 0.0934390971569203, "p99": 0.10815281686064476 }, "ttft": { "mean": 65.01196092181728, "n": 564, "p50": 72.56720603049325, "p95": 86.16573075478665, "p99": 90.08658842061791 } }, "layer1": { "decode_tokens": 501569, "kv_usage_max": 1.0, "kv_usage_mean": 0.9854490932772836, "mode_counts": { "FULL": 3186, "NONE": 237, "PIECEWISE": 5 }, "mode_shares": { "FULL": 0.9294049008168028, "NONE": 0.0691365227537923, "PIECEWISE": 0.0014585764294049008 }, "preemptions": 89, "prefill_tokens": 1616947, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 183, "queue_waiting_mean": 163.93465577596265, "records_all": 6649, "records_clean": 3428, "requests_per_step": { "mean": 91.7362893815636, "n": 3428, "p50": 92.0, "p95": 105.0, "p99": 108.0 }, "scheduled_tokens_per_step": { "mean": 618.0035005834305, "n": 3428, "p50": 92.0, "p95": 8192.0, "p99": 8192.0 }, "step_duration_ms": { "mean": 139.92259133722288, "n": 3428, "p50": 75.726733, "p95": 1011.79896875, "p99": 1094.55223217 }, "token_efficiency_per_ms": 4.416752825095988 }, "layer2_missing_after_controller_cleanup": false, "load": "saturation", "pattern": "P06", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 1.65, "clean_c_waiting_median": 168.0, "completion_rate_rps": 0.1, "completion_rate_within_10pct": false, "tail_end_s": 334.1661366420158, "tail_start_s": 324.1661366420158, "valid": false, "waiting_median": 177.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 1.65, "clean_c_waiting_median": 168.0, "completion_rate_rps": 1.5, "completion_rate_within_10pct": true, "tail_end_s": 367.7157571800053, "tail_start_s": 357.7157571800053, "valid": true, "waiting_median": 174.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 564, "run_dir": "runs/phase3/primary/P06-C00/saturation", "run_id": "P06-C00-saturation", "trace_files": 2, "waste": { "R128": 0.6023504575478206, "R32": 0.5930739622699981, "R64": 0.5988308514107739, "bucket_slack": 0.03675532053452812, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.0691365227537923, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.0691365227537923, "padded_tokens_per_useful_token": 0.005328258082544573, "padding_fraction": 0.03675532053452812 } }, "P06-C01-moderate": { "blocks": [ { "bucket": 2672.0, "duration_ms": 9983.095475, "eligible_miss": 0.0, "miss": 15.0, "model": 292.0, "overflow": 15.0, "padding": 1.0, "tokens": 33391.0 }, { "bucket": 3080.0, "duration_ms": 10144.319392000001, "eligible_miss": 0.0, "miss": 15.0, "model": 295.0, "overflow": 15.0, "padding": 28.0, "tokens": 32556.0 }, { "bucket": 3888.0, "duration_ms": 9834.87609, "eligible_miss": 0.0, "miss": 8.0, "model": 292.0, "overflow": 8.0, "padding": 49.0, "tokens": 19195.0 }, { "bucket": 5000.0, "duration_ms": 10216.316318000003, "eligible_miss": 0.0, "miss": 7.0, "model": 356.0, "overflow": 7.0, "padding": 88.0, "tokens": 19248.0 }, { "bucket": 4400.0, "duration_ms": 10053.599015, "eligible_miss": 0.0, "miss": 7.0, "model": 404.0, "overflow": 7.0, "padding": 25.0, "tokens": 18564.0 }, { "bucket": 3280.0, "duration_ms": 9645.34066100001, "eligible_miss": 0.0, "miss": 9.0, "model": 317.0, "overflow": 9.0, "padding": 42.0, "tokens": 20547.0 }, { "bucket": 3920.0, "duration_ms": 9973.3789, "eligible_miss": 0.0, "miss": 12.0, "model": 293.0, "overflow": 12.0, "padding": 48.0, "tokens": 28448.0 }, { "bucket": 3368.0, "duration_ms": 9980.79801399999, "eligible_miss": 0.0, "miss": 13.0, "model": 302.0, "overflow": 13.0, "padding": 49.0, "tokens": 29315.0 }, { "bucket": 3960.0, "duration_ms": 10001.963437999992, "eligible_miss": 0.0, "miss": 8.0, "model": 325.0, "overflow": 8.0, "padding": 13.0, "tokens": 20331.0 }, { "bucket": 3288.0, "duration_ms": 9961.200092999981, "eligible_miss": 0.0, "miss": 11.0, "model": 318.0, "overflow": 11.0, "padding": 36.0, "tokens": 25058.0 }, { "bucket": 4608.0, "duration_ms": 9977.158559999993, "eligible_miss": 0.0, "miss": 4.0, "model": 415.0, "overflow": 4.0, "padding": 30.0, "tokens": 12344.0 }, { "bucket": 3320.0, "duration_ms": 9407.243992, "eligible_miss": 0.0, "miss": 10.0, "model": 406.0, "overflow": 10.0, "padding": 36.0, "tokens": 22495.0 }, { "bucket": 2992.0, "duration_ms": 10010.801535999995, "eligible_miss": 0.0, "miss": 12.0, "model": 386.0, "overflow": 12.0, "padding": 0.0, "tokens": 27398.0 }, { "bucket": 3832.0, "duration_ms": 9827.609744000005, "eligible_miss": 0.0, "miss": 8.0, "model": 336.0, "overflow": 8.0, "padding": 68.0, "tokens": 20148.0 }, { "bucket": 3120.0, "duration_ms": 9981.477417000004, "eligible_miss": 0.0, "miss": 15.0, "model": 240.0, "overflow": 15.0, "padding": 43.0, "tokens": 32364.0 }, { "bucket": 4688.0, "duration_ms": 9983.903237999999, "eligible_miss": 0.0, "miss": 7.0, "model": 333.0, "overflow": 7.0, "padding": 74.0, "tokens": 17800.0 }, { "bucket": 4280.0, "duration_ms": 9966.367873999996, "eligible_miss": 0.0, "miss": 9.0, "model": 332.0, "overflow": 9.0, "padding": 43.0, "tokens": 22669.0 }, { "bucket": 3632.0, "duration_ms": 9973.898278999997, "eligible_miss": 0.0, "miss": 9.0, "model": 349.0, "overflow": 9.0, "padding": 34.0, "tokens": 21274.0 }, { "bucket": 2480.0, "duration_ms": 10004.851047000002, "eligible_miss": 0.0, "miss": 15.0, "model": 305.0, "overflow": 15.0, "padding": 0.0, "tokens": 30637.0 }, { "bucket": 3112.0, "duration_ms": 10109.527119000008, "eligible_miss": 0.0, "miss": 13.0, "model": 335.0, "overflow": 13.0, "padding": 22.0, "tokens": 29714.0 }, { "bucket": 3176.0, "duration_ms": 10042.397934999999, "eligible_miss": 0.0, "miss": 13.0, "model": 238.0, "overflow": 13.0, "padding": 58.0, "tokens": 29549.0 }, { "bucket": 5336.0, "duration_ms": 9993.305631999996, "eligible_miss": 0.0, "miss": 4.0, "model": 338.0, "overflow": 4.0, "padding": 64.0, "tokens": 13464.0 }, { "bucket": 3968.0, "duration_ms": 9765.116452, "eligible_miss": 0.0, "miss": 8.0, "model": 326.0, "overflow": 8.0, "padding": 34.0, "tokens": 20318.0 }, { "bucket": 3712.0, "duration_ms": 9967.345562000008, "eligible_miss": 0.0, "miss": 12.0, "model": 322.0, "overflow": 12.0, "padding": 47.0, "tokens": 25977.0 }, { "bucket": 4072.0, "duration_ms": 9988.596370999992, "eligible_miss": 0.0, "miss": 9.0, "model": 378.0, "overflow": 9.0, "padding": 52.0, "tokens": 22452.0 }, { "bucket": 3648.0, "duration_ms": 9960.308586000008, "eligible_miss": 0.0, "miss": 9.0, "model": 408.0, "overflow": 9.0, "padding": 35.0, "tokens": 19631.0 }, { "bucket": 3016.0, "duration_ms": 9985.088991000002, "eligible_miss": 0.0, "miss": 12.0, "model": 362.0, "overflow": 12.0, "padding": 21.0, "tokens": 26267.0 }, { "bucket": 3080.0, "duration_ms": 9984.616373000004, "eligible_miss": 0.0, "miss": 12.0, "model": 350.0, "overflow": 12.0, "padding": 3.0, "tokens": 27653.0 }, { "bucket": 3384.0, "duration_ms": 10077.784970999994, "eligible_miss": 0.0, "miss": 11.0, "model": 374.0, "overflow": 11.0, "padding": 43.0, "tokens": 25482.0 }, { "bucket": 4112.0, "duration_ms": 10033.526778999996, "eligible_miss": 0.0, "miss": 7.0, "model": 412.0, "overflow": 7.0, "padding": 35.0, "tokens": 18413.0 }, { "bucket": 3904.0, "duration_ms": 9969.954875999993, "eligible_miss": 0.0, "miss": 9.0, "model": 361.0, "overflow": 9.0, "padding": 37.0, "tokens": 22229.0 }, { "bucket": 4752.0, "duration_ms": 9828.034798999997, "eligible_miss": 0.0, "miss": 3.0, "model": 432.0, "overflow": 3.0, "padding": 44.0, "tokens": 10852.0 }, { "bucket": 2576.0, "duration_ms": 9986.577423, "eligible_miss": 0.0, "miss": 15.0, "model": 323.0, "overflow": 15.0, "padding": 14.0, "tokens": 32355.0 }, { "bucket": 3816.0, "duration_ms": 9964.685290999985, "eligible_miss": 0.0, "miss": 10.0, "model": 357.0, "overflow": 10.0, "padding": 59.0, "tokens": 24237.0 }, { "bucket": 4304.0, "duration_ms": 9969.980953000006, "eligible_miss": 0.0, "miss": 5.0, "model": 466.0, "overflow": 5.0, "padding": 61.0, "tokens": 13096.0 }, { "bucket": 3080.0, "duration_ms": 9643.314677000006, "eligible_miss": 0.0, "miss": 10.0, "model": 397.0, "overflow": 10.0, "padding": 4.0, "tokens": 22061.0 }, { "bucket": 2856.0, "duration_ms": 10174.796019999994, "eligible_miss": 0.0, "miss": 14.0, "model": 371.0, "overflow": 14.0, "padding": 0.0, "tokens": 31528.0 }, { "bucket": 3240.0, "duration_ms": 9782.694661999996, "eligible_miss": 0.0, "miss": 10.0, "model": 386.0, "overflow": 10.0, "padding": 24.0, "tokens": 21500.0 }, { "bucket": 4144.0, "duration_ms": 10109.441436, "eligible_miss": 0.0, "miss": 5.0, "model": 395.0, "overflow": 5.0, "padding": 40.0, "tokens": 14344.0 }, { "bucket": 3480.0, "duration_ms": 9843.460232999998, "eligible_miss": 0.0, "miss": 7.0, "model": 358.0, "overflow": 7.0, "padding": 29.0, "tokens": 16616.0 }, { "bucket": 2760.0, "duration_ms": 9977.245893999998, "eligible_miss": 0.0, "miss": 16.0, "model": 224.0, "overflow": 16.0, "padding": 40.0, "tokens": 34060.0 }, { "bucket": 3400.0, "duration_ms": 10009.148130999996, "eligible_miss": 0.0, "miss": 13.0, "model": 262.0, "overflow": 13.0, "padding": 0.0, "tokens": 28551.0 }, { "bucket": 4048.0, "duration_ms": 9959.503941000004, "eligible_miss": 0.0, "miss": 12.0, "model": 280.0, "overflow": 12.0, "padding": 73.0, "tokens": 28551.0 }, { "bucket": 4488.0, "duration_ms": 9984.051271999997, "eligible_miss": 0.0, "miss": 9.0, "model": 364.0, "overflow": 9.0, "padding": 68.0, "tokens": 21479.0 }, { "bucket": 2880.0, "duration_ms": 9985.313251000007, "eligible_miss": 0.0, "miss": 14.0, "model": 346.0, "overflow": 14.0, "padding": 20.0, "tokens": 30861.0 }, { "bucket": 2952.0, "duration_ms": 10389.374124000002, "eligible_miss": 0.0, "miss": 14.0, "model": 369.0, "overflow": 14.0, "padding": 29.0, "tokens": 30093.0 }, { "bucket": 3488.0, "duration_ms": 9569.878081999996, "eligible_miss": 0.0, "miss": 10.0, "model": 304.0, "overflow": 10.0, "padding": 39.0, "tokens": 23929.0 }, { "bucket": 5152.0, "duration_ms": 10210.717404, "eligible_miss": 0.0, "miss": 4.0, "model": 437.0, "overflow": 4.0, "padding": 80.0, "tokens": 13264.0 } ], "clean": { "admitted": 344, "completed": 336, "completed_throughput_rps": 1.4, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 955216, "offered_rps": 1.4333333333333333, "output_tokens": 172032, "start_s": 60.0 }, "config": "C01", "drain_quarantined": false, "drain_seconds": 4.491966611996759, "latency_s": { "e2e": { "mean": 8.773913019880638, "n": 336, "p50": 8.817151172013837, "p95": 10.46433969050122, "p99": 10.71811510950938 }, "tpot": { "mean": 0.015270867651661564, "n": 336, "p50": 0.015250473021524602, "p95": 0.018393428898271797, "p99": 0.019656831172886448 }, "ttft": { "mean": 0.9704996498815793, "n": 336, "p50": 0.8652395185054047, "p95": 2.05128988873912, "p99": 2.5086708923001417 } }, "layer1": { "decode_tokens": 173853, "kv_usage_max": 0.23274897426333463, "kv_usage_mean": 0.10860699049654005, "mode_counts": { "FULL": 16066, "NONE": 488, "PIECEWISE": 21 }, "mode_shares": { "FULL": 0.969291101055807, "NONE": 0.029441930618401207, "PIECEWISE": 0.0012669683257918551 }, "preemptions": 0, "prefill_tokens": 958455, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 7, "queue_waiting_mean": 0.0856108597285068, "records_all": 23686, "records_clean": 16575, "requests_per_step": { "mean": 10.53628959276018, "n": 16575, "p50": 8.0, "p95": 16.0, "p99": 16.0 }, "scheduled_tokens_per_step": { "mean": 68.31420814479638, "n": 16575, "p50": 8.0, "p95": 16.0, "p99": 2048.0 }, "step_duration_ms": { "mean": 28.850315916923076, "n": 16575, "p50": 19.387058, "p95": 29.4861622, "p99": 291.6603715399994 }, "token_efficiency_per_ms": 2.3678842318923965 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P06", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 1.6, "clean_c_waiting_median": 0.0, "completion_rate_rps": 1.6, "completion_rate_within_10pct": true, "tail_end_s": 341.8995923009934, "tail_start_s": 331.8995923009934, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 1.6, "clean_c_waiting_median": 0.0, "completion_rate_rps": 1.6, "completion_rate_within_10pct": true, "tail_end_s": 373.7317875540175, "tail_start_s": 363.7317875540175, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": true, "requests_completed": 336, "run_dir": "runs/phase3/primary/P06-C01/moderate", "run_id": "P06-C01-moderate", "trace_files": 2, "waste": { "R128": 0.6023504575478206, "R32": 0.5930739622699981, "R64": 0.5988308514107739, "bucket_slack": 0.010139748725418792, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.029207651922032465, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 501, "moe_layer_cv": null, "overflow_rate": 0.029207651922032465, "padded_tokens_per_useful_token": 0.001573776746256319, "padding_fraction": 0.010139748725418792 } }, "P06-C01-saturation": { "blocks": [ { "bucket": 6904.0, "duration_ms": 9418.292302000007, "eligible_miss": 0.0, "miss": 13.0, "model": 77.0, "overflow": 13.0, "padding": 188.0, "tokens": 31910.0 }, { "bucket": 10648.0, "duration_ms": 9994.622971000003, "eligible_miss": 0.0, "miss": 4.0, "model": 109.0, "overflow": 4.0, "padding": 398.0, "tokens": 17851.0 }, { "bucket": 12576.0, "duration_ms": 10008.333585999999, "eligible_miss": 0.0, "miss": 0.0, "model": 131.0, "overflow": 0.0, "padding": 233.0, "tokens": 12343.0 }, { "bucket": 7280.0, "duration_ms": 10245.870207, "eligible_miss": 0.0, "miss": 14.0, "model": 90.0, "overflow": 14.0, "padding": 268.0, "tokens": 34239.0 }, { "duration_ms": 10108.830802, "eligible_miss": 0.0, "miss": 30.0, "model": 30.0, "overflow": 30.0, "tokens": 61440.0 }, { "duration_ms": 9833.619431999998, "eligible_miss": 0.0, "miss": 29.0, "model": 29.0, "overflow": 29.0, "tokens": 59392.0 }, { "duration_ms": 10136.308064999997, "eligible_miss": 0.0, "miss": 30.0, "model": 30.0, "overflow": 30.0, "tokens": 61440.0 }, { "duration_ms": 9738.182761, "eligible_miss": 0.0, "miss": 29.0, "model": 29.0, "overflow": 29.0, "tokens": 59392.0 }, { "bucket": 4160.0, "duration_ms": 9903.814556, "eligible_miss": 0.0, "miss": 19.0, "model": 59.0, "overflow": 19.0, "padding": 72.0, "tokens": 42229.0 }, { "bucket": 12896.0, "duration_ms": 10019.929632999998, "eligible_miss": 0.0, "miss": 0.0, "model": 124.0, "overflow": 0.0, "padding": 551.0, "tokens": 12345.0 }, { "bucket": 12216.0, "duration_ms": 9991.564728000001, "eligible_miss": 0.0, "miss": 0.0, "model": 127.0, "overflow": 0.0, "padding": 183.0, "tokens": 12033.0 }, { "bucket": 7760.0, "duration_ms": 10099.811674000006, "eligible_miss": 0.0, "miss": 12.0, "model": 89.0, "overflow": 12.0, "padding": 419.0, "tokens": 30410.0 }, { "duration_ms": 9986.679154000001, "eligible_miss": 0.0, "miss": 29.0, "model": 29.0, "overflow": 29.0, "tokens": 59392.0 }, { "duration_ms": 9952.167458000002, "eligible_miss": 0.0, "miss": 30.0, "model": 30.0, "overflow": 30.0, "tokens": 61440.0 }, { "duration_ms": 10194.748773000003, "eligible_miss": 0.0, "miss": 30.0, "model": 30.0, "overflow": 30.0, "tokens": 61440.0 }, { "duration_ms": 9892.233782000003, "eligible_miss": 0.0, "miss": 29.0, "model": 29.0, "overflow": 29.0, "tokens": 59392.0 }, { "bucket": 5152.0, "duration_ms": 10279.543559000002, "eligible_miss": 0.0, "miss": 20.0, "model": 66.0, "overflow": 20.0, "padding": 277.0, "tokens": 44672.0 }, { "bucket": 12168.0, "duration_ms": 9531.385584999995, "eligible_miss": 0.0, "miss": 1.0, "model": 117.0, "overflow": 1.0, "padding": 392.0, "tokens": 13685.0 }, { "bucket": 12376.0, "duration_ms": 9952.329975, "eligible_miss": 0.0, "miss": 2.0, "model": 120.0, "overflow": 2.0, "padding": 636.0, "tokens": 15205.0 }, { "bucket": 9600.0, "duration_ms": 10234.776673999999, "eligible_miss": 0.0, "miss": 9.0, "model": 109.0, "overflow": 9.0, "padding": 216.0, "tokens": 26935.0 }, { "duration_ms": 10098.437773000001, "eligible_miss": 0.0, "miss": 30.0, "model": 30.0, "overflow": 30.0, "tokens": 61440.0 }, { "duration_ms": 10149.765926, "eligible_miss": 0.0, "miss": 30.0, "model": 30.0, "overflow": 30.0, "tokens": 61440.0 }, { "duration_ms": 9781.945214, "eligible_miss": 0.0, "miss": 29.0, "model": 29.0, "overflow": 29.0, "tokens": 59392.0 }, { "duration_ms": 10055.906094999998, "eligible_miss": 0.0, "miss": 30.0, "model": 30.0, "overflow": 30.0, "tokens": 61440.0 }, { "bucket": 4224.0, "duration_ms": 9670.510049999997, "eligible_miss": 0.0, "miss": 18.0, "model": 62.0, "overflow": 18.0, "padding": 153.0, "tokens": 39980.0 }, { "bucket": 12288.0, "duration_ms": 9951.205562000006, "eligible_miss": 0.0, "miss": 0.0, "model": 128.0, "overflow": 0.0, "padding": 658.0, "tokens": 11630.0 }, { "bucket": 12040.0, "duration_ms": 9984.624423999998, "eligible_miss": 0.0, "miss": 0.0, "model": 130.0, "overflow": 0.0, "padding": 571.0, "tokens": 11469.0 }, { "bucket": 6160.0, "duration_ms": 10267.234748, "eligible_miss": 0.0, "miss": 15.0, "model": 85.0, "overflow": 15.0, "padding": 104.0, "tokens": 35685.0 }, { "duration_ms": 10186.587034000002, "eligible_miss": 0.0, "miss": 29.0, "model": 29.0, "overflow": 29.0, "tokens": 59392.0 }, { "duration_ms": 9887.492626, "eligible_miss": 0.0, "miss": 29.0, "model": 29.0, "overflow": 29.0, "tokens": 59392.0 }, { "duration_ms": 9782.122324, "eligible_miss": 0.0, "miss": 29.0, "model": 29.0, "overflow": 29.0, "tokens": 59392.0 }, { "duration_ms": 10100.028454, "eligible_miss": 0.0, "miss": 30.0, "model": 30.0, "overflow": 30.0, "tokens": 61440.0 }, { "bucket": 5896.0, "duration_ms": 9748.447406000001, "eligible_miss": 0.0, "miss": 15.0, "model": 71.0, "overflow": 15.0, "padding": 225.0, "tokens": 36391.0 }, { "bucket": 12272.0, "duration_ms": 10042.153232000008, "eligible_miss": 0.0, "miss": 2.0, "model": 120.0, "overflow": 2.0, "padding": 656.0, "tokens": 14848.0 }, { "bucket": 10760.0, "duration_ms": 9964.378218999997, "eligible_miss": 0.0, "miss": 4.0, "model": 111.0, "overflow": 4.0, "padding": 439.0, "tokens": 17856.0 }, { "bucket": 9120.0, "duration_ms": 10090.992645999999, "eligible_miss": 0.0, "miss": 9.0, "model": 104.0, "overflow": 9.0, "padding": 167.0, "tokens": 25996.0 }, { "duration_ms": 10061.783895, "eligible_miss": 0.0, "miss": 30.0, "model": 30.0, "overflow": 30.0, "tokens": 60197.0 }, { "duration_ms": 10226.395404999997, "eligible_miss": 0.0, "miss": 30.0, "model": 30.0, "overflow": 30.0, "tokens": 61440.0 }, { "duration_ms": 9836.990006, "eligible_miss": 0.0, "miss": 30.0, "model": 30.0, "overflow": 30.0, "tokens": 61440.0 }, { "duration_ms": 10073.936996, "eligible_miss": 0.0, "miss": 29.0, "model": 29.0, "overflow": 29.0, "tokens": 59392.0 }, { "bucket": 3608.0, "duration_ms": 9672.199914999997, "eligible_miss": 0.0, "miss": 20.0, "model": 61.0, "overflow": 20.0, "padding": 0.0, "tokens": 43169.0 }, { "bucket": 11088.0, "duration_ms": 10005.363535, "eligible_miss": 0.0, "miss": 2.0, "model": 128.0, "overflow": 2.0, "padding": 191.0, "tokens": 14398.0 }, { "bucket": 11528.0, "duration_ms": 9979.159297999999, "eligible_miss": 0.0, "miss": 0.0, "model": 131.0, "overflow": 0.0, "padding": 414.0, "tokens": 11114.0 }, { "bucket": 6488.0, "duration_ms": 10210.046228000001, "eligible_miss": 0.0, "miss": 14.0, "model": 88.0, "overflow": 14.0, "padding": 415.0, "tokens": 33466.0 }, { "duration_ms": 10130.624972, "eligible_miss": 0.0, "miss": 29.0, "model": 29.0, "overflow": 29.0, "tokens": 59392.0 }, { "duration_ms": 9761.507399999999, "eligible_miss": 0.0, "miss": 29.0, "model": 29.0, "overflow": 29.0, "tokens": 59392.0 }, { "duration_ms": 10248.139619, "eligible_miss": 0.0, "miss": 30.0, "model": 30.0, "overflow": 30.0, "tokens": 61440.0 }, { "duration_ms": 9801.388455, "eligible_miss": 0.0, "miss": 28.0, "model": 28.0, "overflow": 28.0, "tokens": 57344.0 } ], "clean": { "admitted": 566, "completed": 566, "completed_throughput_rps": 2.3583333333333334, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 1637559, "offered_rps": 2.3583333333333334, "output_tokens": 289792, "start_s": 60.0 }, "config": "C01", "drain_quarantined": false, "drain_seconds": 98.6341013039928, "latency_s": { "e2e": { "mean": 106.76549268240902, "n": 566, "p50": 112.07339421949291, "p95": 130.40440611923987, "p99": 135.57815159696622 }, "tpot": { "mean": 0.07499950729258756, "n": 566, "p50": 0.07366898813504892, "p95": 0.08367265785228196, "p99": 0.10166048986216235 }, "ttft": { "mean": 68.44074445589678, "n": 566, "p50": 74.25358793899068, "p95": 91.44885190949572, "p99": 96.69285478206731 } }, "layer1": { "decode_tokens": 413751, "kv_usage_max": 1.0, "kv_usage_mean": 0.9691897666726189, "mode_counts": { "FULL": 2240, "NONE": 900, "PIECEWISE": 4 }, "mode_shares": { "FULL": 0.712468193384224, "NONE": 0.2862595419847328, "PIECEWISE": 0.001272264631043257 }, "preemptions": 46, "prefill_tokens": 1622801, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 181, "queue_waiting_mean": 163.7395038167939, "records_all": 6363, "records_clean": 3144, "requests_per_step": { "mean": 91.90044529262086, "n": 3144, "p50": 92.0, "p95": 102.0, "p99": 106.0 }, "scheduled_tokens_per_step": { "mean": 647.7582697201018, "n": 3144, "p50": 98.0, "p95": 2048.0, "p99": 2048.0 }, "step_duration_ms": { "mean": 152.44669628944018, "n": 3144, "p50": 79.9125085, "p95": 365.08051875, "p99": 395.60820568 }, "token_efficiency_per_ms": 4.2490804030954346 }, "layer2_missing_after_controller_cleanup": false, "load": "saturation", "pattern": "P06", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 2.25, "clean_c_waiting_median": 169.0, "completion_rate_rps": 4.3, "completion_rate_within_10pct": false, "tail_end_s": 349.72332530099084, "tail_start_s": 339.72332530099084, "valid": false, "waiting_median": 176.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 2.25, "clean_c_waiting_median": 169.0, "completion_rate_rps": 4.0, "completion_rate_within_10pct": false, "tail_end_s": 400.2956078030111, "tail_start_s": 390.2956078030111, "valid": false, "waiting_median": 180.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 566, "run_dir": "runs/phase3/primary/P06-C01/saturation", "run_id": "P06-C01-saturation", "trace_files": 2, "waste": { "R128": 0.6023504575478206, "R32": 0.5930739622699981, "R64": 0.5988308514107739, "bucket_slack": 0.03570125177913215, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.2862595419847328, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.2862595419847328, "padded_tokens_per_useful_token": 0.003842769543817197, "padding_fraction": 0.03570125177913215 } }, "P06-C10-moderate": { "blocks": [ { "bucket": 2984.0, "duration_ms": 9968.688442999994, "eligible_miss": 0.0, "miss": 5.0, "model": 293.0, "overflow": 5.0, "padding": 9.0, "tokens": 33676.0 }, { "bucket": 3072.0, "duration_ms": 9999.67704899999, "eligible_miss": 0.0, "miss": 5.0, "model": 241.0, "overflow": 5.0, "padding": 0.0, "tokens": 32895.0 }, { "bucket": 4456.0, "duration_ms": 9985.151113999997, "eligible_miss": 0.0, "miss": 2.0, "model": 329.0, "overflow": 2.0, "padding": 15.0, "tokens": 19737.0 }, { "bucket": 3832.0, "duration_ms": 9958.370330000002, "eligible_miss": 0.0, "miss": 3.0, "model": 324.0, "overflow": 3.0, "padding": 23.0, "tokens": 26537.0 }, { "bucket": 3440.0, "duration_ms": 9982.292306000003, "eligible_miss": 0.0, "miss": 3.0, "model": 340.0, "overflow": 3.0, "padding": 0.0, "tokens": 27035.0 }, { "bucket": 3160.0, "duration_ms": 9981.709315999999, "eligible_miss": 1.0, "miss": 4.0, "model": 325.0, "overflow": 3.0, "padding": 7.0, "tokens": 28132.0 }, { "bucket": 3640.0, "duration_ms": 9979.026379999996, "eligible_miss": 0.0, "miss": 4.0, "model": 354.0, "overflow": 4.0, "padding": 7.0, "tokens": 29531.0 }, { "bucket": 3632.0, "duration_ms": 9998.650812999997, "eligible_miss": 1.0, "miss": 3.0, "model": 339.0, "overflow": 2.0, "padding": 14.0, "tokens": 20209.0 }, { "bucket": 4152.0, "duration_ms": 10839.769605000001, "eligible_miss": 0.0, "miss": 3.0, "model": 362.0, "overflow": 3.0, "padding": 10.0, "tokens": 25857.0 }, { "bucket": 4168.0, "duration_ms": 9557.040489000003, "eligible_miss": 0.0, "miss": 1.0, "model": 380.0, "overflow": 1.0, "padding": 10.0, "tokens": 11897.0 }, { "bucket": 5128.0, "duration_ms": 9451.50596200001, "eligible_miss": 0.0, "miss": 0.0, "model": 510.0, "overflow": 0.0, "padding": 6.0, "tokens": 5122.0 }, { "bucket": 2296.0, "duration_ms": 9415.719377999993, "eligible_miss": 2.0, "miss": 6.0, "model": 293.0, "overflow": 4.0, "padding": 0.0, "tokens": 35631.0 }, { "bucket": 3376.0, "duration_ms": 9974.437237000004, "eligible_miss": 0.0, "miss": 4.0, "model": 291.0, "overflow": 4.0, "padding": 20.0, "tokens": 30094.0 }, { "bucket": 3200.0, "duration_ms": 9996.377144000007, "eligible_miss": 0.0, "miss": 5.0, "model": 269.0, "overflow": 5.0, "padding": 0.0, "tokens": 32361.0 }, { "bucket": 4448.0, "duration_ms": 9968.941337, "eligible_miss": 0.0, "miss": 2.0, "model": 337.0, "overflow": 2.0, "padding": 11.0, "tokens": 17928.0 }, { "bucket": 3752.0, "duration_ms": 9978.026393, "eligible_miss": 1.0, "miss": 4.0, "model": 322.0, "overflow": 3.0, "padding": 17.0, "tokens": 22903.0 }, { "bucket": 3784.0, "duration_ms": 9992.190155999993, "eligible_miss": 0.0, "miss": 3.0, "model": 376.0, "overflow": 3.0, "padding": 6.0, "tokens": 21390.0 }, { "bucket": 2712.0, "duration_ms": 10144.682894000003, "eligible_miss": 0.0, "miss": 5.0, "model": 321.0, "overflow": 5.0, "padding": 11.0, "tokens": 30739.0 }, { "bucket": 3512.0, "duration_ms": 10679.815315, "eligible_miss": 0.0, "miss": 4.0, "model": 345.0, "overflow": 4.0, "padding": 6.0, "tokens": 36274.0 }, { "bucket": 3216.0, "duration_ms": 9468.849742000002, "eligible_miss": 0.0, "miss": 4.0, "model": 241.0, "overflow": 4.0, "padding": 15.0, "tokens": 23435.0 }, { "bucket": 4872.0, "duration_ms": 10371.413924999999, "eligible_miss": 0.0, "miss": 2.0, "model": 340.0, "overflow": 2.0, "padding": 15.0, "tokens": 21241.0 }, { "bucket": 4016.0, "duration_ms": 9233.718109, "eligible_miss": 1.0, "miss": 2.0, "model": 336.0, "overflow": 1.0, "padding": 7.0, "tokens": 12652.0 }, { "bucket": 4000.0, "duration_ms": 9964.93926299999, "eligible_miss": 0.0, "miss": 3.0, "model": 345.0, "overflow": 3.0, "padding": 13.0, "tokens": 26186.0 }, { "bucket": 3992.0, "duration_ms": 9983.514276999982, "eligible_miss": 0.0, "miss": 3.0, "model": 390.0, "overflow": 3.0, "padding": 9.0, "tokens": 22490.0 }, { "bucket": 3824.0, "duration_ms": 9967.431117999991, "eligible_miss": 0.0, "miss": 3.0, "model": 414.0, "overflow": 3.0, "padding": 8.0, "tokens": 19770.0 }, { "bucket": 3104.0, "duration_ms": 9987.400416000002, "eligible_miss": 1.0, "miss": 4.0, "model": 339.0, "overflow": 3.0, "padding": 5.0, "tokens": 26275.0 }, { "bucket": 3408.0, "duration_ms": 9969.86757, "eligible_miss": 0.0, "miss": 3.0, "model": 317.0, "overflow": 3.0, "padding": 2.0, "tokens": 27982.0 }, { "bucket": 3800.0, "duration_ms": 9983.764680000006, "eligible_miss": 0.0, "miss": 3.0, "model": 364.0, "overflow": 3.0, "padding": 11.0, "tokens": 25846.0 }, { "bucket": 3168.0, "duration_ms": 9992.213853, "eligible_miss": 0.0, "miss": 4.0, "model": 344.0, "overflow": 4.0, "padding": 12.0, "tokens": 31647.0 }, { "bucket": 4288.0, "duration_ms": 9963.092042, "eligible_miss": 0.0, "miss": 2.0, "model": 396.0, "overflow": 2.0, "padding": 6.0, "tokens": 14924.0 }, { "bucket": 4080.0, "duration_ms": 10617.837592, "eligible_miss": 0.0, "miss": 3.0, "model": 412.0, "overflow": 3.0, "padding": 6.0, "tokens": 28650.0 }, { "bucket": 3264.0, "duration_ms": 9873.84534800001, "eligible_miss": 0.0, "miss": 3.0, "model": 376.0, "overflow": 3.0, "padding": 2.0, "tokens": 24735.0 }, { "bucket": 4440.0, "duration_ms": 9427.799631999995, "eligible_miss": 0.0, "miss": 1.0, "model": 421.0, "overflow": 1.0, "padding": 12.0, "tokens": 8453.0 }, { "bucket": 4592.0, "duration_ms": 9966.856386999998, "eligible_miss": 0.0, "miss": 2.0, "model": 492.0, "overflow": 2.0, "padding": 13.0, "tokens": 13393.0 }, { "bucket": 3068.0, "duration_ms": 9315.430008000005, "eligible_miss": 0.0, "miss": 3.0, "model": 387.0, "overflow": 3.0, "padding": 1.0, "tokens": 22030.0 }, { "bucket": 2544.0, "duration_ms": 9980.105680000008, "eligible_miss": 0.0, "miss": 5.0, "model": 285.0, "overflow": 5.0, "padding": 9.0, "tokens": 36537.0 }, { "bucket": 4280.0, "duration_ms": 9989.648308, "eligible_miss": 1.0, "miss": 3.0, "model": 357.0, "overflow": 2.0, "padding": 12.0, "tokens": 17052.0 }, { "bucket": 3496.0, "duration_ms": 9983.011968999996, "eligible_miss": 0.0, "miss": 3.0, "model": 340.0, "overflow": 3.0, "padding": 8.0, "tokens": 26788.0 }, { "bucket": 2536.0, "duration_ms": 9973.913760000001, "eligible_miss": 0.0, "miss": 4.0, "model": 283.0, "overflow": 4.0, "padding": 0.0, "tokens": 33733.0 }, { "bucket": 3384.0, "duration_ms": 9981.835801000007, "eligible_miss": 1.0, "miss": 4.0, "model": 292.0, "overflow": 3.0, "padding": 7.0, "tokens": 28419.0 }, { "bucket": 3776.0, "duration_ms": 10016.567731000003, "eligible_miss": 1.0, "miss": 4.0, "model": 294.0, "overflow": 3.0, "padding": 12.0, "tokens": 28608.0 }, { "bucket": 4504.0, "duration_ms": 9950.887116000002, "eligible_miss": 0.0, "miss": 3.0, "model": 380.0, "overflow": 3.0, "padding": 8.0, "tokens": 21490.0 }, { "bucket": 4784.0, "duration_ms": 11398.240730999998, "eligible_miss": 0.0, "miss": 3.0, "model": 471.0, "overflow": 3.0, "padding": 13.0, "tokens": 29347.0 }, { "bucket": 3400.0, "duration_ms": 9854.494030000007, "eligible_miss": 0.0, "miss": 3.0, "model": 391.0, "overflow": 3.0, "padding": 12.0, "tokens": 23089.0 }, { "bucket": 2960.0, "duration_ms": 8671.937073, "eligible_miss": 1.0, "miss": 3.0, "model": 255.0, "overflow": 2.0, "padding": 11.0, "tokens": 19835.0 }, { "bucket": 4712.0, "duration_ms": 9964.669994000005, "eligible_miss": 0.0, "miss": 2.0, "model": 377.0, "overflow": 2.0, "padding": 20.0, "tokens": 19049.0 }, { "bucket": 3576.0, "duration_ms": 9977.808734999995, "eligible_miss": 0.0, "miss": 3.0, "model": 374.0, "overflow": 3.0, "padding": 2.0, "tokens": 25329.0 }, { "bucket": 2728.0, "duration_ms": 9983.505524999997, "eligible_miss": 0.0, "miss": 5.0, "model": 263.0, "overflow": 5.0, "padding": 7.0, "tokens": 37252.0 } ], "clean": { "admitted": 352, "completed": 352, "completed_throughput_rps": 1.4666666666666666, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 991279, "offered_rps": 1.4666666666666666, "output_tokens": 180224, "start_s": 60.0 }, "config": "C10", "drain_quarantined": false, "drain_seconds": 4.380946171004325, "latency_s": { "e2e": { "mean": 8.521981804951297, "n": 352, "p50": 8.611102025490254, "p95": 10.042639616953966, "p99": 10.376431019741284 }, "tpot": { "mean": 0.014745414302892397, "n": 352, "p50": 0.01479352528180147, "p95": 0.01784971316144328, "p99": 0.018753809229155375 }, "ttft": { "mean": 0.9870750961732814, "n": 352, "p50": 1.0108699320117012, "p95": 1.8988438446089275, "p99": 2.218485610165226 } }, "layer1": { "decode_tokens": 177688, "kv_usage_max": 0.21875312219002896, "kv_usage_mean": 0.1036769300750604, "mode_counts": { "FULL": 16470, "NONE": 160, "PIECEWISE": 1 }, "mode_shares": { "FULL": 0.9903192832661897, "NONE": 0.009620588058445073, "PIECEWISE": 6.01286753652817e-05 }, "preemptions": 0, "prefill_tokens": 1006497, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 6, "queue_waiting_mean": 0.014911911490589862, "records_all": 24869, "records_clean": 16631, "requests_per_step": { "mean": 10.711201972220552, "n": 16631, "p50": 8.0, "p95": 16.0, "p99": 16.0 }, "scheduled_tokens_per_step": { "mean": 71.20347543743611, "n": 16631, "p50": 8.0, "p95": 16.0, "p99": 16.0 }, "step_duration_ms": { "mean": 28.721464258072277, "n": 16631, "p50": 19.530679, "p95": 28.7628175, "p99": 301.7449877000092 }, "token_efficiency_per_ms": 2.479103251757929 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P06", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 1.6, "clean_c_waiting_median": 0.0, "completion_rate_rps": 1.6, "completion_rate_within_10pct": true, "tail_end_s": 331.32366371300304, "tail_start_s": 321.32366371300304, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 1.6, "clean_c_waiting_median": 0.0, "completion_rate_rps": 1.6, "completion_rate_within_10pct": true, "tail_end_s": 362.93273995199706, "tail_start_s": 352.93273995199706, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": true, "requests_completed": 352, "run_dir": "runs/phase3/primary/P06-C10/moderate", "run_id": "P06-C10-moderate", "trace_files": 2, "waste": { "R128": 0.6023504575478206, "R32": 0.5930739622699981, "R64": 0.5988308514107739, "bucket_slack": 0.00284059447606813, "eligible_miss_rate": 0.0006615745474228664, "graph_miss_rate": 0.009382329945269743, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 155, "moe_layer_cv": null, "overflow_rate": 0.008720755397846875, "padded_tokens_per_useful_token": 0.0003631189383415598, "padding_fraction": 0.0024354878905276513 } }, "P06-C10-saturation": { "blocks": [ { "duration_ms": 10184.668676000001, "eligible_miss": 2.0, "miss": 15.0, "model": 15.0, "overflow": 13.0, "tokens": 75610.0 }, { "bucket": 3712.0, "duration_ms": 8871.553595999998, "eligible_miss": 0.0, "miss": 5.0, "model": 63.0, "overflow": 5.0, "padding": 0.0, "tokens": 43504.0 }, { "bucket": 10752.0, "duration_ms": 9944.392154999996, "eligible_miss": 0.0, "miss": 0.0, "model": 168.0, "overflow": 0.0, "padding": 0.0, "tokens": 10752.0 }, { "bucket": 10496.0, "duration_ms": 9989.546154, "eligible_miss": 0.0, "miss": 0.0, "model": 164.0, "overflow": 0.0, "padding": 0.0, "tokens": 10496.0 }, { "bucket": 5888.0, "duration_ms": 11067.204580000001, "eligible_miss": 3.0, "miss": 10.0, "model": 102.0, "overflow": 7.0, "padding": 1.0, "tokens": 48983.0 }, { "duration_ms": 9496.656133000002, "eligible_miss": 1.0, "miss": 10.0, "model": 10.0, "overflow": 9.0, "tokens": 73458.0 }, { "bucket": 896.0, "duration_ms": 9422.229260000002, "eligible_miss": 1.0, "miss": 11.0, "model": 25.0, "overflow": 10.0, "padding": 0.0, "tokens": 64392.0 }, { "bucket": 11200.0, "duration_ms": 10010.468302999998, "eligible_miss": 0.0, "miss": 0.0, "model": 175.0, "overflow": 0.0, "padding": 0.0, "tokens": 11200.0 }, { "bucket": 10944.0, "duration_ms": 9975.989317999994, "eligible_miss": 0.0, "miss": 0.0, "model": 171.0, "overflow": 0.0, "padding": 0.0, "tokens": 10944.0 }, { "bucket": 7808.0, "duration_ms": 10552.635057000001, "eligible_miss": 2.0, "miss": 7.0, "model": 129.0, "overflow": 5.0, "padding": 1.0, "tokens": 34660.0 }, { "duration_ms": 9884.066383000001, "eligible_miss": 0.0, "miss": 12.0, "model": 12.0, "overflow": 12.0, "tokens": 75141.0 }, { "bucket": 64.0, "duration_ms": 9923.407183999998, "eligible_miss": 0.0, "miss": 13.0, "model": 14.0, "overflow": 13.0, "padding": 0.0, "tokens": 72823.0 }, { "bucket": 11008.0, "duration_ms": 9593.384500999997, "eligible_miss": 0.0, "miss": 0.0, "model": 172.0, "overflow": 0.0, "padding": 0.0, "tokens": 11008.0 }, { "bucket": 11072.0, "duration_ms": 9989.240422999997, "eligible_miss": 0.0, "miss": 0.0, "model": 173.0, "overflow": 0.0, "padding": 0.0, "tokens": 11072.0 }, { "bucket": 8704.0, "duration_ms": 10628.489381000001, "eligible_miss": 2.0, "miss": 6.0, "model": 142.0, "overflow": 4.0, "padding": 4.0, "tokens": 30665.0 }, { "duration_ms": 9825.908395999999, "eligible_miss": 1.0, "miss": 13.0, "model": 13.0, "overflow": 12.0, "tokens": 75749.0 }, { "duration_ms": 10510.417456000001, "eligible_miss": 0.0, "miss": 13.0, "model": 13.0, "overflow": 13.0, "tokens": 78441.0 }, { "bucket": 10112.0, "duration_ms": 9049.764061999997, "eligible_miss": 0.0, "miss": 0.0, "model": 158.0, "overflow": 0.0, "padding": 0.0, "tokens": 10112.0 }, { "bucket": 11136.0, "duration_ms": 9938.462914999998, "eligible_miss": 0.0, "miss": 0.0, "model": 174.0, "overflow": 0.0, "padding": 0.0, "tokens": 11136.0 }, { "bucket": 9472.0, "duration_ms": 10972.880893000001, "eligible_miss": 1.0, "miss": 4.0, "model": 152.0, "overflow": 3.0, "padding": 1.0, "tokens": 31022.0 }, { "duration_ms": 10338.176429, "eligible_miss": 0.0, "miss": 13.0, "model": 13.0, "overflow": 13.0, "tokens": 79069.0 }, { "duration_ms": 9218.303395, "eligible_miss": 1.0, "miss": 11.0, "model": 11.0, "overflow": 10.0, "tokens": 66925.0 }, { "bucket": 6272.0, "duration_ms": 9481.264913000005, "eligible_miss": 1.0, "miss": 5.0, "model": 103.0, "overflow": 4.0, "padding": 0.0, "tokens": 35279.0 }, { "bucket": 11392.0, "duration_ms": 9944.188837000003, "eligible_miss": 0.0, "miss": 0.0, "model": 178.0, "overflow": 0.0, "padding": 0.0, "tokens": 11392.0 }, { "bucket": 11136.0, "duration_ms": 10002.603861000005, "eligible_miss": 0.0, "miss": 0.0, "model": 174.0, "overflow": 0.0, "padding": 0.0, "tokens": 11136.0 }, { "bucket": 1920.0, "duration_ms": 10572.825789999999, "eligible_miss": 2.0, "miss": 12.0, "model": 42.0, "overflow": 10.0, "padding": 1.0, "tokens": 69902.0 }, { "duration_ms": 10003.447610000001, "eligible_miss": 1.0, "miss": 13.0, "model": 13.0, "overflow": 12.0, "tokens": 69136.0 }, { "bucket": 1984.0, "duration_ms": 9449.084334, "eligible_miss": 0.0, "miss": 9.0, "model": 40.0, "overflow": 9.0, "padding": 0.0, "tokens": 60721.0 }, { "bucket": 10880.0, "duration_ms": 9949.095603, "eligible_miss": 0.0, "miss": 0.0, "model": 170.0, "overflow": 0.0, "padding": 0.0, "tokens": 10880.0 }, { "bucket": 10816.0, "duration_ms": 10024.887996000001, "eligible_miss": 0.0, "miss": 0.0, "model": 169.0, "overflow": 0.0, "padding": 0.0, "tokens": 10816.0 }, { "bucket": 6976.0, "duration_ms": 10451.003526999995, "eligible_miss": 3.0, "miss": 10.0, "model": 119.0, "overflow": 7.0, "padding": 1.0, "tokens": 35730.0 }, { "duration_ms": 10420.409311, "eligible_miss": 2.0, "miss": 14.0, "model": 14.0, "overflow": 12.0, "tokens": 81494.0 }, { "bucket": 64.0, "duration_ms": 9135.379603, "eligible_miss": 0.0, "miss": 10.0, "model": 11.0, "overflow": 10.0, "padding": 0.0, "tokens": 64970.0 }, { "bucket": 11520.0, "duration_ms": 9928.713835, "eligible_miss": 0.0, "miss": 0.0, "model": 180.0, "overflow": 0.0, "padding": 0.0, "tokens": 11520.0 }, { "bucket": 11328.0, "duration_ms": 9972.419044999999, "eligible_miss": 0.0, "miss": 0.0, "model": 177.0, "overflow": 0.0, "padding": 0.0, "tokens": 11328.0 }, { "bucket": 7744.0, "duration_ms": 10875.907865000003, "eligible_miss": 1.0, "miss": 7.0, "model": 128.0, "overflow": 6.0, "padding": 1.0, "tokens": 40810.0 }, { "duration_ms": 9818.483750000001, "eligible_miss": 0.0, "miss": 12.0, "model": 12.0, "overflow": 12.0, "tokens": 74921.0 }, { "duration_ms": 10055.352617999999, "eligible_miss": 2.0, "miss": 13.0, "model": 13.0, "overflow": 11.0, "tokens": 76325.0 }, { "bucket": 6080.0, "duration_ms": 9237.526175, "eligible_miss": 0.0, "miss": 3.0, "model": 98.0, "overflow": 3.0, "padding": 0.0, "tokens": 29721.0 }, { "bucket": 10688.0, "duration_ms": 9993.652559, "eligible_miss": 0.0, "miss": 0.0, "model": 167.0, "overflow": 0.0, "padding": 0.0, "tokens": 10688.0 }, { "bucket": 10496.0, "duration_ms": 10020.391325999997, "eligible_miss": 0.0, "miss": 0.0, "model": 164.0, "overflow": 0.0, "padding": 0.0, "tokens": 10496.0 }, { "bucket": 3328.0, "duration_ms": 10926.115058, "eligible_miss": 1.0, "miss": 11.0, "model": 63.0, "overflow": 10.0, "padding": 1.0, "tokens": 62223.0 }, { "duration_ms": 9090.596137999999, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 67808.0 }, { "bucket": 1664.0, "duration_ms": 9942.095380999996, "eligible_miss": 4.0, "miss": 14.0, "model": 40.0, "overflow": 10.0, "padding": 0.0, "tokens": 63097.0 }, { "bucket": 10816.0, "duration_ms": 9981.973696000003, "eligible_miss": 0.0, "miss": 0.0, "model": 169.0, "overflow": 0.0, "padding": 0.0, "tokens": 10816.0 }, { "bucket": 10560.0, "duration_ms": 9974.256657000002, "eligible_miss": 0.0, "miss": 0.0, "model": 165.0, "overflow": 0.0, "padding": 0.0, "tokens": 10560.0 }, { "bucket": 7552.0, "duration_ms": 10682.932023000003, "eligible_miss": 0.0, "miss": 5.0, "model": 123.0, "overflow": 5.0, "padding": 1.0, "tokens": 35997.0 }, { "duration_ms": 9975.763851000002, "eligible_miss": 3.0, "miss": 13.0, "model": 13.0, "overflow": 10.0, "tokens": 73687.0 } ], "clean": { "admitted": 583, "completed": 583, "completed_throughput_rps": 2.4291666666666667, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 1706195, "offered_rps": 2.4291666666666667, "output_tokens": 298496, "start_s": 60.0 }, "config": "C10", "drain_quarantined": false, "drain_seconds": 95.53387634200044, "latency_s": { "e2e": { "mean": 101.3565315140522, "n": 583, "p50": 104.58615519001614, "p95": 114.11084459880075, "p99": 118.06476088725671 }, "tpot": { "mean": 0.04984293034401163, "n": 583, "p50": 0.049699737217209855, "p95": 0.0539970578847181, "p99": 0.05502665809392811 }, "ttft": { "mean": 75.88679410826225, "n": 583, "p50": 79.60525833698921, "p95": 89.27045010388537, "p99": 93.5858921495825 } }, "layer1": { "decode_tokens": 294516, "kv_usage_max": 0.7428314516934759, "kv_usage_mean": 0.6299692841321703, "mode_counts": { "FULL": 4320, "NONE": 304 }, "mode_shares": { "FULL": 0.9342560553633218, "NONE": 0.0657439446366782 }, "preemptions": 0, "prefill_tokens": 1694099, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 197, "queue_waiting_mean": 191.90376297577853, "records_all": 8763, "records_clean": 4624, "requests_per_step": { "mean": 63.84407439446367, "n": 4624, "p50": 64.0, "p95": 64.0, "p99": 64.0 }, "scheduled_tokens_per_step": { "mean": 430.06379757785464, "n": 4624, "p50": 64.0, "p95": 2907.5999999999585, "p99": 8192.0 }, "step_duration_ms": { "mean": 103.6544584801038, "n": 4624, "p50": 58.3942475, "p95": 540.7021005499993, "p99": 1052.19412524 }, "token_efficiency_per_ms": 4.149013982455991 }, "layer2_missing_after_controller_cleanup": false, "load": "saturation", "pattern": "P06", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 1.7, "clean_c_waiting_median": 192.0, "completion_rate_rps": 3.7, "completion_rate_within_10pct": false, "tail_end_s": 355.943668923981, "tail_start_s": 345.943668923981, "valid": false, "waiting_median": 192.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 1.7, "clean_c_waiting_median": 192.0, "completion_rate_rps": 2.5, "completion_rate_within_10pct": false, "tail_end_s": 389.65710150499945, "tail_start_s": 379.65710150499945, "valid": false, "waiting_median": 192.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 583, "run_dir": "runs/phase3/primary/P06-C10/saturation", "run_id": "P06-C10-saturation", "trace_files": 2, "waste": { "R128": 0.6023504575478206, "R32": 0.5930739622699981, "R64": 0.5988308514107739, "bucket_slack": 0.0009259002385840316, "eligible_miss_rate": 0.007352941176470588, "graph_miss_rate": 0.0657439446366782, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.05839100346020761, "padded_tokens_per_useful_token": 6.03435054045152e-06, "padding_fraction": 4.340277777777778e-05 } }, "P06-C11-moderate": { "blocks": [ { "bucket": 2784.0, "duration_ms": 9991.795590999998, "eligible_miss": 0.0, "miss": 15.0, "model": 289.0, "overflow": 15.0, "padding": 1.0, "tokens": 33503.0 }, { "bucket": 2496.0, "duration_ms": 9984.000759000004, "eligible_miss": 1.0, "miss": 16.0, "model": 285.0, "overflow": 15.0, "padding": 34.0, "tokens": 32430.0 }, { "bucket": 4056.0, "duration_ms": 9979.876596999997, "eligible_miss": 0.0, "miss": 8.0, "model": 300.0, "overflow": 8.0, "padding": 49.0, "tokens": 19363.0 }, { "bucket": 4240.0, "duration_ms": 10347.565718000002, "eligible_miss": 1.0, "miss": 10.0, "model": 338.0, "overflow": 9.0, "padding": 78.0, "tokens": 23048.0 }, { "bucket": 4024.0, "duration_ms": 9814.699700000014, "eligible_miss": 0.0, "miss": 7.0, "model": 390.0, "overflow": 7.0, "padding": 14.0, "tokens": 18199.0 }, { "bucket": 3608.0, "duration_ms": 9772.572115999996, "eligible_miss": 0.0, "miss": 7.0, "model": 342.0, "overflow": 7.0, "padding": 42.0, "tokens": 17030.0 }, { "bucket": 3504.0, "duration_ms": 9976.144115999994, "eligible_miss": 0.0, "miss": 13.0, "model": 301.0, "overflow": 13.0, "padding": 44.0, "tokens": 28542.0 }, { "bucket": 3320.0, "duration_ms": 9971.772360999998, "eligible_miss": 0.0, "miss": 13.0, "model": 295.0, "overflow": 13.0, "padding": 45.0, "tokens": 29271.0 }, { "bucket": 3776.0, "duration_ms": 10005.948374999994, "eligible_miss": 1.0, "miss": 9.0, "model": 313.0, "overflow": 8.0, "padding": 7.0, "tokens": 20428.0 }, { "bucket": 3296.0, "duration_ms": 9975.181751, "eligible_miss": 0.0, "miss": 11.0, "model": 312.0, "overflow": 11.0, "padding": 29.0, "tokens": 25073.0 }, { "bucket": 4680.0, "duration_ms": 9966.712054000003, "eligible_miss": 0.0, "miss": 4.0, "model": 417.0, "overflow": 4.0, "padding": 63.0, "tokens": 12383.0 }, { "bucket": 2872.0, "duration_ms": 9521.160925, "eligible_miss": 0.0, "miss": 13.0, "model": 372.0, "overflow": 13.0, "padding": 3.0, "tokens": 28224.0 }, { "bucket": 2968.0, "duration_ms": 10163.028479999995, "eligible_miss": 0.0, "miss": 13.0, "model": 384.0, "overflow": 13.0, "padding": 0.0, "tokens": 29422.0 }, { "bucket": 3560.0, "duration_ms": 9863.206437, "eligible_miss": 1.0, "miss": 10.0, "model": 329.0, "overflow": 9.0, "padding": 62.0, "tokens": 20722.0 }, { "bucket": 3504.0, "duration_ms": 9738.622831, "eligible_miss": 0.0, "miss": 10.0, "model": 271.0, "overflow": 10.0, "padding": 43.0, "tokens": 23939.0 }, { "bucket": 4400.0, "duration_ms": 9974.671073000001, "eligible_miss": 0.0, "miss": 7.0, "model": 335.0, "overflow": 7.0, "padding": 60.0, "tokens": 17889.0 }, { "bucket": 3480.0, "duration_ms": 9981.279874999998, "eligible_miss": 0.0, "miss": 10.0, "model": 336.0, "overflow": 10.0, "padding": 24.0, "tokens": 22694.0 }, { "bucket": 3656.0, "duration_ms": 9969.817867000003, "eligible_miss": 0.0, "miss": 9.0, "model": 353.0, "overflow": 9.0, "padding": 33.0, "tokens": 21299.0 }, { "bucket": 2688.0, "duration_ms": 9981.607506999997, "eligible_miss": 0.0, "miss": 15.0, "model": 290.0, "overflow": 15.0, "padding": 0.0, "tokens": 30845.0 }, { "bucket": 2456.0, "duration_ms": 10210.062520999998, "eligible_miss": 0.0, "miss": 17.0, "model": 299.0, "overflow": 17.0, "padding": 22.0, "tokens": 37250.0 }, { "bucket": 3600.0, "duration_ms": 9763.962257999996, "eligible_miss": 0.0, "miss": 9.0, "model": 269.0, "overflow": 9.0, "padding": 58.0, "tokens": 21899.0 }, { "bucket": 4344.0, "duration_ms": 10347.414697999997, "eligible_miss": 0.0, "miss": 9.0, "model": 309.0, "overflow": 9.0, "padding": 55.0, "tokens": 22721.0 }, { "bucket": 4088.0, "duration_ms": 10040.395758999999, "eligible_miss": 0.0, "miss": 9.0, "model": 356.0, "overflow": 9.0, "padding": 38.0, "tokens": 19686.0 }, { "bucket": 4048.0, "duration_ms": 9530.296545999996, "eligible_miss": 0.0, "miss": 7.0, "model": 361.0, "overflow": 7.0, "padding": 43.0, "tokens": 17378.0 }, { "bucket": 3760.0, "duration_ms": 9977.245639000013, "eligible_miss": 1.0, "miss": 10.0, "model": 363.0, "overflow": 9.0, "padding": 50.0, "tokens": 22300.0 }, { "bucket": 3784.0, "duration_ms": 9964.184954999999, "eligible_miss": 0.0, "miss": 8.0, "model": 397.0, "overflow": 8.0, "padding": 35.0, "tokens": 19756.0 }, { "bucket": 2960.0, "duration_ms": 9980.599558000002, "eligible_miss": 2.0, "miss": 13.0, "model": 347.0, "overflow": 11.0, "padding": 18.0, "tokens": 26224.0 }, { "bucket": 3136.0, "duration_ms": 9993.791949, "eligible_miss": 1.0, "miss": 13.0, "model": 322.0, "overflow": 12.0, "padding": 0.0, "tokens": 27865.0 }, { "bucket": 3424.0, "duration_ms": 9958.501031, "eligible_miss": 0.0, "miss": 11.0, "model": 361.0, "overflow": 11.0, "padding": 45.0, "tokens": 25520.0 }, { "bucket": 3312.0, "duration_ms": 10133.055848, "eligible_miss": 0.0, "miss": 12.0, "model": 359.0, "overflow": 12.0, "padding": 31.0, "tokens": 27857.0 }, { "bucket": 3904.0, "duration_ms": 9830.097450000003, "eligible_miss": 1.0, "miss": 8.0, "model": 373.0, "overflow": 7.0, "padding": 33.0, "tokens": 18494.0 }, { "bucket": 4840.0, "duration_ms": 10346.134011999995, "eligible_miss": 0.0, "miss": 4.0, "model": 469.0, "overflow": 4.0, "padding": 37.0, "tokens": 12995.0 }, { "bucket": 2808.0, "duration_ms": 9589.825538000006, "eligible_miss": 0.0, "miss": 11.0, "model": 346.0, "overflow": 11.0, "padding": 14.0, "tokens": 24395.0 }, { "bucket": 3904.0, "duration_ms": 9980.938999999978, "eligible_miss": 0.0, "miss": 10.0, "model": 366.0, "overflow": 10.0, "padding": 59.0, "tokens": 24325.0 }, { "bucket": 4296.0, "duration_ms": 9970.991288999987, "eligible_miss": 0.0, "miss": 5.0, "model": 464.0, "overflow": 5.0, "padding": 61.0, "tokens": 13088.0 }, { "bucket": 3104.0, "duration_ms": 9654.592499000011, "eligible_miss": 0.0, "miss": 10.0, "model": 400.0, "overflow": 10.0, "padding": 4.0, "tokens": 22085.0 }, { "bucket": 2320.0, "duration_ms": 9985.013716000003, "eligible_miss": 0.0, "miss": 17.0, "model": 301.0, "overflow": 17.0, "padding": 30.0, "tokens": 36415.0 }, { "bucket": 3800.0, "duration_ms": 9975.918895999994, "eligible_miss": 0.0, "miss": 7.0, "model": 397.0, "overflow": 7.0, "padding": 0.0, "tokens": 16638.0 }, { "bucket": 3248.0, "duration_ms": 10256.340521999995, "eligible_miss": 0.0, "miss": 12.0, "model": 327.0, "overflow": 12.0, "padding": 40.0, "tokens": 26613.0 }, { "bucket": 3624.0, "duration_ms": 9876.904798999998, "eligible_miss": 0.0, "miss": 7.0, "model": 361.0, "overflow": 7.0, "padding": 30.0, "tokens": 17930.0 }, { "bucket": 3320.0, "duration_ms": 10086.872195000005, "eligible_miss": 0.0, "miss": 12.0, "model": 286.0, "overflow": 12.0, "padding": 40.0, "tokens": 26428.0 }, { "bucket": 3816.0, "duration_ms": 9703.728442000009, "eligible_miss": 0.0, "miss": 10.0, "model": 263.0, "overflow": 10.0, "padding": 59.0, "tokens": 22764.0 }, { "bucket": 3784.0, "duration_ms": 9980.674858999995, "eligible_miss": 1.0, "miss": 13.0, "model": 288.0, "overflow": 12.0, "padding": 45.0, "tokens": 28685.0 }, { "bucket": 4288.0, "duration_ms": 9975.193013000007, "eligible_miss": 0.0, "miss": 9.0, "model": 389.0, "overflow": 9.0, "padding": 43.0, "tokens": 21304.0 }, { "bucket": 2888.0, "duration_ms": 9985.337101999998, "eligible_miss": 0.0, "miss": 14.0, "model": 336.0, "overflow": 14.0, "padding": 29.0, "tokens": 30860.0 }, { "bucket": 2368.0, "duration_ms": 9982.161468000002, "eligible_miss": 0.0, "miss": 17.0, "model": 284.0, "overflow": 17.0, "padding": 0.0, "tokens": 35682.0 }, { "bucket": 4384.0, "duration_ms": 9980.502426000003, "eligible_miss": 1.0, "miss": 8.0, "model": 366.0, "overflow": 7.0, "padding": 39.0, "tokens": 18763.0 }, { "bucket": 3800.0, "duration_ms": 10233.927156, "eligible_miss": 0.0, "miss": 11.0, "model": 356.0, "overflow": 11.0, "padding": 80.0, "tokens": 25562.0 } ], "clean": { "admitted": 344, "completed": 336, "completed_throughput_rps": 1.4, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 955216, "offered_rps": 1.4333333333333333, "output_tokens": 172032, "start_s": 60.0 }, "config": "C11", "drain_quarantined": false, "drain_seconds": 3.233019929000875, "latency_s": { "e2e": { "mean": 8.811718997470356, "n": 336, "p50": 8.860830737001379, "p95": 10.438232306754799, "p99": 10.661098391610722 }, "tpot": { "mean": 0.015341037308058707, "n": 336, "p50": 0.015262965586132356, "p95": 0.018323992875227187, "p99": 0.019567817679344728 }, "ttft": { "mean": 0.9724489330523544, "n": 336, "p50": 0.8726355374965351, "p95": 2.050784301252861, "p99": 2.5037182233965716 } }, "layer1": { "decode_tokens": 173763, "kv_usage_max": 0.21429622724819708, "kv_usage_mean": 0.1012056417269781, "mode_counts": { "FULL": 15859, "NONE": 507, "PIECEWISE": 5 }, "mode_shares": { "FULL": 0.968725184777961, "NONE": 0.030969397104636247, "PIECEWISE": 0.0003054181174027243 }, "preemptions": 0, "prefill_tokens": 972023, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 7, "queue_waiting_mean": 0.08826583592938733, "records_all": 23855, "records_clean": 16371, "requests_per_step": { "mean": 10.662696231140432, "n": 16371, "p50": 8.0, "p95": 16.0, "p99": 16.0 }, "scheduled_tokens_per_step": { "mean": 69.98876061327958, "n": 16371, "p50": 8.0, "p95": 16.0, "p99": 2048.0 }, "step_duration_ms": { "mean": 29.214729049966408, "n": 16371, "p50": 19.582729, "p95": 29.3386855, "p99": 293.3203081 }, "token_efficiency_per_ms": 2.3956669423008075 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P06", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 1.6, "clean_c_waiting_median": 0.0, "completion_rate_rps": 1.6, "completion_rate_within_10pct": true, "tail_end_s": 331.74715706999996, "tail_start_s": 321.74715706999996, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 1.6, "clean_c_waiting_median": 0.0, "completion_rate_rps": 0.8, "completion_rate_within_10pct": false, "tail_end_s": 363.41947703200276, "tail_start_s": 353.41947703200276, "valid": false, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 336, "run_dir": "runs/phase3/primary/P06-C11/moderate", "run_id": "P06-C11-moderate", "trace_files": 2, "waste": { "R128": 0.6023504575478206, "R32": 0.5930739622699981, "R64": 0.5988308514107739, "bucket_slack": 0.010014462145906983, "eligible_miss_rate": 0.0006720840716075029, "graph_miss_rate": 0.030732571638052177, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 504, "moe_layer_cv": null, "overflow_rate": 0.030060487566444676, "padded_tokens_per_useful_token": 0.0014566419907382356, "padding_fraction": 0.009799201503053077 } }, "P06-C11-saturation": { "blocks": [ { "bucket": 192.0, "duration_ms": 10082.961571000002, "eligible_miss": 3.0, "miss": 33.0, "model": 36.0, "overflow": 30.0, "padding": 3.0, "tokens": 60243.0 }, { "bucket": 960.0, "duration_ms": 9944.095406, "eligible_miss": 3.0, "miss": 32.0, "model": 47.0, "overflow": 29.0, "padding": 10.0, "tokens": 54480.0 }, { "bucket": 832.0, "duration_ms": 9730.454249000002, "eligible_miss": 0.0, "miss": 28.0, "model": 41.0, "overflow": 28.0, "padding": 0.0, "tokens": 56909.0 }, { "bucket": 10688.0, "duration_ms": 10026.303037000005, "eligible_miss": 0.0, "miss": 0.0, "model": 167.0, "overflow": 0.0, "padding": 0.0, "tokens": 10688.0 }, { "bucket": 10432.0, "duration_ms": 9986.693028999998, "eligible_miss": 0.0, "miss": 0.0, "model": 163.0, "overflow": 0.0, "padding": 0.0, "tokens": 10432.0 }, { "bucket": 3648.0, "duration_ms": 10226.678839000002, "eligible_miss": 2.0, "miss": 24.0, "model": 81.0, "overflow": 22.0, "padding": 12.0, "tokens": 45900.0 }, { "bucket": 384.0, "duration_ms": 9925.763535999999, "eligible_miss": 1.0, "miss": 30.0, "model": 36.0, "overflow": 29.0, "padding": 5.0, "tokens": 59966.0 }, { "bucket": 576.0, "duration_ms": 10225.903192999996, "eligible_miss": 2.0, "miss": 32.0, "model": 41.0, "overflow": 30.0, "padding": 8.0, "tokens": 59654.0 }, { "bucket": 6464.0, "duration_ms": 9584.442423999999, "eligible_miss": 0.0, "miss": 12.0, "model": 113.0, "overflow": 12.0, "padding": 2.0, "tokens": 29715.0 }, { "bucket": 10880.0, "duration_ms": 9960.685231999996, "eligible_miss": 0.0, "miss": 0.0, "model": 170.0, "overflow": 0.0, "padding": 0.0, "tokens": 10880.0 }, { "bucket": 8128.0, "duration_ms": 10558.448065000004, "eligible_miss": 2.0, "miss": 12.0, "model": 139.0, "overflow": 10.0, "padding": 9.0, "tokens": 26886.0 }, { "bucket": 256.0, "duration_ms": 9654.425447000003, "eligible_miss": 0.0, "miss": 30.0, "model": 34.0, "overflow": 30.0, "padding": 6.0, "tokens": 58128.0 }, { "bucket": 768.0, "duration_ms": 10016.586984000001, "eligible_miss": 0.0, "miss": 32.0, "model": 44.0, "overflow": 32.0, "padding": 13.0, "tokens": 59666.0 }, { "bucket": 3136.0, "duration_ms": 9749.143122000003, "eligible_miss": 2.0, "miss": 24.0, "model": 73.0, "overflow": 22.0, "padding": 7.0, "tokens": 46471.0 }, { "bucket": 11264.0, "duration_ms": 10010.441336999997, "eligible_miss": 0.0, "miss": 0.0, "model": 176.0, "overflow": 0.0, "padding": 0.0, "tokens": 11264.0 }, { "bucket": 10688.0, "duration_ms": 9979.167980999999, "eligible_miss": 1.0, "miss": 2.0, "model": 169.0, "overflow": 1.0, "padding": 2.0, "tokens": 11707.0 }, { "bucket": 1088.0, "duration_ms": 10111.994275000005, "eligible_miss": 2.0, "miss": 31.0, "model": 48.0, "overflow": 29.0, "padding": 18.0, "tokens": 57957.0 }, { "bucket": 640.0, "duration_ms": 10101.266452000002, "eligible_miss": 2.0, "miss": 33.0, "model": 43.0, "overflow": 31.0, "padding": 7.0, "tokens": 58422.0 }, { "bucket": 256.0, "duration_ms": 9945.284613999998, "eligible_miss": 0.0, "miss": 31.0, "model": 35.0, "overflow": 31.0, "padding": 2.0, "tokens": 62645.0 }, { "bucket": 10432.0, "duration_ms": 9836.099997999996, "eligible_miss": 1.0, "miss": 2.0, "model": 165.0, "overflow": 1.0, "padding": 0.0, "tokens": 12659.0 }, { "bucket": 11008.0, "duration_ms": 9939.759173, "eligible_miss": 0.0, "miss": 0.0, "model": 172.0, "overflow": 0.0, "padding": 0.0, "tokens": 11008.0 }, { "bucket": 3776.0, "duration_ms": 10179.827958999998, "eligible_miss": 3.0, "miss": 24.0, "model": 83.0, "overflow": 21.0, "padding": 10.0, "tokens": 45969.0 }, { "bucket": 320.0, "duration_ms": 10209.444457000001, "eligible_miss": 1.0, "miss": 31.0, "model": 36.0, "overflow": 30.0, "padding": 3.0, "tokens": 61439.0 }, { "bucket": 576.0, "duration_ms": 9864.660417000001, "eligible_miss": 2.0, "miss": 30.0, "model": 39.0, "overflow": 28.0, "padding": 6.0, "tokens": 57207.0 }, { "bucket": 3200.0, "duration_ms": 9742.562434000005, "eligible_miss": 1.0, "miss": 22.0, "model": 72.0, "overflow": 21.0, "padding": 3.0, "tokens": 44364.0 }, { "bucket": 10880.0, "duration_ms": 10003.151557000001, "eligible_miss": 0.0, "miss": 0.0, "model": 170.0, "overflow": 0.0, "padding": 0.0, "tokens": 10880.0 }, { "bucket": 10176.0, "duration_ms": 10321.144609999998, "eligible_miss": 0.0, "miss": 3.0, "model": 162.0, "overflow": 3.0, "padding": 1.0, "tokens": 15280.0 }, { "bucket": 896.0, "duration_ms": 10135.580694999999, "eligible_miss": 3.0, "miss": 31.0, "model": 45.0, "overflow": 28.0, "padding": 9.0, "tokens": 55560.0 }, { "bucket": 192.0, "duration_ms": 9969.717403999999, "eligible_miss": 1.0, "miss": 30.0, "model": 33.0, "overflow": 29.0, "padding": 3.0, "tokens": 58681.0 }, { "bucket": 896.0, "duration_ms": 9658.526538000002, "eligible_miss": 2.0, "miss": 30.0, "model": 44.0, "overflow": 28.0, "padding": 11.0, "tokens": 53798.0 }, { "bucket": 5376.0, "duration_ms": 9859.479598999997, "eligible_miss": 0.0, "miss": 15.0, "model": 99.0, "overflow": 15.0, "padding": 1.0, "tokens": 34693.0 }, { "bucket": 10688.0, "duration_ms": 10015.031904, "eligible_miss": 0.0, "miss": 0.0, "model": 167.0, "overflow": 0.0, "padding": 0.0, "tokens": 10688.0 }, { "bucket": 8896.0, "duration_ms": 10145.63891, "eligible_miss": 2.0, "miss": 8.0, "model": 147.0, "overflow": 6.0, "padding": 6.0, "tokens": 19153.0 }, { "bucket": 960.0, "duration_ms": 9868.575407999999, "eligible_miss": 4.0, "miss": 31.0, "model": 46.0, "overflow": 27.0, "padding": 12.0, "tokens": 53598.0 }, { "bucket": 448.0, "duration_ms": 10157.341323999999, "eligible_miss": 2.0, "miss": 33.0, "model": 40.0, "overflow": 31.0, "padding": 5.0, "tokens": 62763.0 }, { "bucket": 960.0, "duration_ms": 9793.570380999998, "eligible_miss": 2.0, "miss": 29.0, "model": 44.0, "overflow": 27.0, "padding": 2.0, "tokens": 55034.0 }, { "bucket": 10944.0, "duration_ms": 9956.056209, "eligible_miss": 0.0, "miss": 0.0, "model": 171.0, "overflow": 0.0, "padding": 0.0, "tokens": 10944.0 }, { "bucket": 10816.0, "duration_ms": 9998.52987, "eligible_miss": 0.0, "miss": 0.0, "model": 169.0, "overflow": 0.0, "padding": 0.0, "tokens": 10816.0 }, { "bucket": 2304.0, "duration_ms": 10328.584660000002, "eligible_miss": 2.0, "miss": 29.0, "model": 65.0, "overflow": 27.0, "padding": 8.0, "tokens": 52481.0 }, { "bucket": 256.0, "duration_ms": 9895.535402000001, "eligible_miss": 2.0, "miss": 32.0, "model": 36.0, "overflow": 30.0, "padding": 3.0, "tokens": 58504.0 }, { "bucket": 704.0, "duration_ms": 10133.923506000001, "eligible_miss": 4.0, "miss": 33.0, "model": 44.0, "overflow": 29.0, "padding": 12.0, "tokens": 57857.0 }, { "bucket": 1728.0, "duration_ms": 9642.673120000001, "eligible_miss": 1.0, "miss": 24.0, "model": 51.0, "overflow": 23.0, "padding": 0.0, "tokens": 49241.0 }, { "bucket": 10496.0, "duration_ms": 9969.511140999995, "eligible_miss": 0.0, "miss": 0.0, "model": 164.0, "overflow": 0.0, "padding": 0.0, "tokens": 10496.0 }, { "bucket": 10304.0, "duration_ms": 9971.499231000002, "eligible_miss": 0.0, "miss": 0.0, "model": 161.0, "overflow": 0.0, "padding": 0.0, "tokens": 10304.0 }, { "bucket": 1856.0, "duration_ms": 10479.133187, "eligible_miss": 0.0, "miss": 28.0, "model": 57.0, "overflow": 28.0, "padding": 7.0, "tokens": 55542.0 }, { "bucket": 192.0, "duration_ms": 9845.170644999998, "eligible_miss": 1.0, "miss": 30.0, "model": 33.0, "overflow": 29.0, "padding": 4.0, "tokens": 58977.0 }, { "bucket": 952.0, "duration_ms": 9922.926027000003, "eligible_miss": 2.0, "miss": 31.0, "model": 45.0, "overflow": 29.0, "padding": 11.0, "tokens": 54863.0 }, { "bucket": 5568.0, "duration_ms": 9766.356098, "eligible_miss": 3.0, "miss": 17.0, "model": 104.0, "overflow": 14.0, "padding": 7.0, "tokens": 31661.0 } ], "clean": { "admitted": 568, "completed": 568, "completed_throughput_rps": 2.3666666666666667, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 1643843, "offered_rps": 2.3666666666666667, "output_tokens": 290816, "start_s": 60.0 }, "config": "C11", "drain_quarantined": false, "drain_seconds": 101.96125678598764, "latency_s": { "e2e": { "mean": 105.60085378511151, "n": 568, "p50": 109.96654033550294, "p95": 121.63363380308728, "p99": 126.2996933970525 }, "tpot": { "mean": 0.053216996705190735, "n": 568, "p50": 0.053181282284747264, "p95": 0.05820221032573622, "p99": 0.05901893801076068 }, "ttft": { "mean": 78.40696846875905, "n": 568, "p50": 83.40565797999443, "p95": 95.05179660475405, "p99": 100.46216534071517 } }, "layer1": { "decode_tokens": 273535, "kv_usage_max": 0.7332090467546485, "kv_usage_mean": 0.6163612764631382, "mode_counts": { "FULL": 3390, "NONE": 929, "PIECEWISE": 1 }, "mode_shares": { "FULL": 0.7847222222222222, "NONE": 0.2150462962962963, "PIECEWISE": 0.0002314814814814815 }, "preemptions": 0, "prefill_tokens": 1642938, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 201, "queue_waiting_mean": 192.1122685185185, "records_all": 8397, "records_clean": 4320, "requests_per_step": { "mean": 63.62453703703704, "n": 4320, "p50": 64.0, "p95": 64.0, "p99": 64.0 }, "scheduled_tokens_per_step": { "mean": 443.6280092592593, "n": 4320, "p50": 64.0, "p95": 2048.0, "p99": 2048.0 }, "step_duration_ms": { "mean": 110.97934042986111, "n": 4320, "p50": 59.9869195, "p95": 338.55503250000004, "p99": 371.98406197 }, "token_efficiency_per_ms": 3.9973927358095263 }, "layer2_missing_after_controller_cleanup": false, "load": "saturation", "pattern": "P06", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 3.1, "clean_c_waiting_median": 192.0, "completion_rate_rps": 2.3, "completion_rate_within_10pct": false, "tail_end_s": 333.1218382779916, "tail_start_s": 323.1218382779916, "valid": false, "waiting_median": 192.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 3.1, "clean_c_waiting_median": 192.0, "completion_rate_rps": 2.3, "completion_rate_within_10pct": false, "tail_end_s": 366.2731193389918, "tail_start_s": 356.2731193389918, "valid": false, "waiting_median": 192.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 568, "run_dir": "runs/phase3/primary/P06-C11/saturation", "run_id": "P06-C11-saturation", "trace_files": 2, "waste": { "R128": 0.6023504575478206, "R32": 0.5930739622699981, "R64": 0.5988308514107739, "bucket_slack": 0.002611677510228721, "eligible_miss_rate": 0.013657407407407408, "graph_miss_rate": 0.2150462962962963, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.2013888888888889, "padded_tokens_per_useful_token": 0.00011896854273449195, "padding_fraction": 0.0010503040353786622 } }, "P07-C00-moderate": { "blocks": [ { "bucket": 7296.0, "duration_ms": 9971.907498999997, "eligible_miss": 0.0, "miss": 4.0, "model": 290.0, "overflow": 4.0, "padding": 12.0, "tokens": 27872.0 }, { "bucket": 7536.0, "duration_ms": 9985.334541999999, "eligible_miss": 0.0, "miss": 4.0, "model": 285.0, "overflow": 4.0, "padding": 12.0, "tokens": 28112.0 }, { "bucket": 7664.0, "duration_ms": 9979.916429000008, "eligible_miss": 0.0, "miss": 4.0, "model": 283.0, "overflow": 4.0, "padding": 12.0, "tokens": 28240.0 }, { "bucket": 8112.0, "duration_ms": 9987.633896000001, "eligible_miss": 0.0, "miss": 4.0, "model": 307.0, "overflow": 4.0, "padding": 12.0, "tokens": 28688.0 }, { "bucket": 7664.0, "duration_ms": 9980.657777999997, "eligible_miss": 0.0, "miss": 4.0, "model": 304.0, "overflow": 4.0, "padding": 12.0, "tokens": 28240.0 }, { "bucket": 7640.0, "duration_ms": 9962.675201000004, "eligible_miss": 0.0, "miss": 4.0, "model": 301.0, "overflow": 4.0, "padding": 12.0, "tokens": 28216.0 }, { "bucket": 7256.0, "duration_ms": 9975.330927, "eligible_miss": 0.0, "miss": 5.0, "model": 283.0, "overflow": 5.0, "padding": 6.0, "tokens": 27864.0 }, { "bucket": 7912.0, "duration_ms": 9979.580427, "eligible_miss": 0.0, "miss": 4.0, "model": 303.0, "overflow": 4.0, "padding": 12.0, "tokens": 28488.0 }, { "bucket": 8152.0, "duration_ms": 9976.500125999999, "eligible_miss": 0.0, "miss": 4.0, "model": 323.0, "overflow": 4.0, "padding": 14.0, "tokens": 28726.0 }, { "bucket": 8104.0, "duration_ms": 10161.867221999993, "eligible_miss": 0.0, "miss": 4.0, "model": 344.0, "overflow": 4.0, "padding": 12.0, "tokens": 28658.0 }, { "bucket": 7720.0, "duration_ms": 10428.90538799999, "eligible_miss": 0.0, "miss": 4.0, "model": 327.0, "overflow": 4.0, "padding": 6.0, "tokens": 28286.0 }, { "bucket": 7712.0, "duration_ms": 9321.163778999997, "eligible_miss": 0.0, "miss": 2.0, "model": 312.0, "overflow": 2.0, "padding": 12.0, "tokens": 17994.0 }, { "bucket": 7432.0, "duration_ms": 9997.364576000002, "eligible_miss": 0.0, "miss": 4.0, "model": 290.0, "overflow": 4.0, "padding": 12.0, "tokens": 28008.0 }, { "bucket": 7704.0, "duration_ms": 9968.157033000007, "eligible_miss": 0.0, "miss": 4.0, "model": 292.0, "overflow": 4.0, "padding": 12.0, "tokens": 28280.0 }, { "bucket": 8016.0, "duration_ms": 9983.975116999996, "eligible_miss": 0.0, "miss": 4.0, "model": 313.0, "overflow": 4.0, "padding": 12.0, "tokens": 28592.0 }, { "bucket": 7344.0, "duration_ms": 9979.674523000003, "eligible_miss": 0.0, "miss": 4.0, "model": 293.0, "overflow": 4.0, "padding": 12.0, "tokens": 27920.0 }, { "bucket": 7672.0, "duration_ms": 9975.575549000001, "eligible_miss": 0.0, "miss": 4.0, "model": 292.0, "overflow": 4.0, "padding": 12.0, "tokens": 28247.0 }, { "bucket": 7864.0, "duration_ms": 9992.28741, "eligible_miss": 0.0, "miss": 4.0, "model": 302.0, "overflow": 4.0, "padding": 11.0, "tokens": 28441.0 }, { "bucket": 7952.0, "duration_ms": 9958.252177000008, "eligible_miss": 0.0, "miss": 4.0, "model": 318.0, "overflow": 4.0, "padding": 12.0, "tokens": 28528.0 }, { "bucket": 7744.0, "duration_ms": 9988.906290000008, "eligible_miss": 0.0, "miss": 4.0, "model": 328.0, "overflow": 4.0, "padding": 12.0, "tokens": 28300.0 }, { "bucket": 7392.0, "duration_ms": 9994.193122000002, "eligible_miss": 0.0, "miss": 4.0, "model": 311.0, "overflow": 4.0, "padding": 6.0, "tokens": 27958.0 }, { "bucket": 7808.0, "duration_ms": 10226.192321999995, "eligible_miss": 0.0, "miss": 4.0, "model": 316.0, "overflow": 4.0, "padding": 8.0, "tokens": 28388.0 }, { "bucket": 8248.0, "duration_ms": 10417.59643, "eligible_miss": 0.0, "miss": 4.0, "model": 328.0, "overflow": 4.0, "padding": 12.0, "tokens": 28824.0 }, { "bucket": 8008.0, "duration_ms": 9272.779190000003, "eligible_miss": 0.0, "miss": 2.0, "model": 323.0, "overflow": 2.0, "padding": 12.0, "tokens": 18290.0 }, { "bucket": 7696.0, "duration_ms": 9975.396886000011, "eligible_miss": 0.0, "miss": 4.0, "model": 316.0, "overflow": 4.0, "padding": 12.0, "tokens": 28272.0 }, { "bucket": 7688.0, "duration_ms": 9974.740527999995, "eligible_miss": 0.0, "miss": 4.0, "model": 318.0, "overflow": 4.0, "padding": 12.0, "tokens": 28264.0 }, { "bucket": 7608.0, "duration_ms": 10001.287686999993, "eligible_miss": 0.0, "miss": 4.0, "model": 315.0, "overflow": 4.0, "padding": 12.0, "tokens": 28184.0 }, { "bucket": 7768.0, "duration_ms": 9973.692631000007, "eligible_miss": 0.0, "miss": 5.0, "model": 324.0, "overflow": 5.0, "padding": 12.0, "tokens": 28370.0 }, { "bucket": 7528.0, "duration_ms": 9966.926483999992, "eligible_miss": 0.0, "miss": 4.0, "model": 317.0, "overflow": 4.0, "padding": 6.0, "tokens": 28096.0 }, { "bucket": 7320.0, "duration_ms": 9979.419324999995, "eligible_miss": 0.0, "miss": 4.0, "model": 295.0, "overflow": 4.0, "padding": 14.0, "tokens": 27894.0 }, { "bucket": 7592.0, "duration_ms": 9984.026474999999, "eligible_miss": 0.0, "miss": 4.0, "model": 296.0, "overflow": 4.0, "padding": 6.0, "tokens": 28170.0 }, { "bucket": 7736.0, "duration_ms": 9996.897663000005, "eligible_miss": 0.0, "miss": 4.0, "model": 304.0, "overflow": 4.0, "padding": 12.0, "tokens": 28312.0 }, { "bucket": 8032.0, "duration_ms": 9989.042325, "eligible_miss": 0.0, "miss": 4.0, "model": 324.0, "overflow": 4.0, "padding": 8.0, "tokens": 28612.0 }, { "bucket": 8728.0, "duration_ms": 10264.222522000005, "eligible_miss": 0.0, "miss": 4.0, "model": 382.0, "overflow": 4.0, "padding": 18.0, "tokens": 29266.0 }, { "bucket": 7776.0, "duration_ms": 10385.723340000006, "eligible_miss": 0.0, "miss": 4.0, "model": 356.0, "overflow": 4.0, "padding": 12.0, "tokens": 28320.0 }, { "bucket": 7616.0, "duration_ms": 9266.232714000002, "eligible_miss": 0.0, "miss": 2.0, "model": 323.0, "overflow": 2.0, "padding": 6.0, "tokens": 17888.0 }, { "bucket": 7504.0, "duration_ms": 9968.152762999998, "eligible_miss": 0.0, "miss": 4.0, "model": 313.0, "overflow": 4.0, "padding": 12.0, "tokens": 28064.0 }, { "bucket": 8136.0, "duration_ms": 9974.840383000006, "eligible_miss": 0.0, "miss": 4.0, "model": 336.0, "overflow": 4.0, "padding": 12.0, "tokens": 28712.0 }, { "bucket": 8064.0, "duration_ms": 9986.361588000007, "eligible_miss": 0.0, "miss": 4.0, "model": 359.0, "overflow": 4.0, "padding": 12.0, "tokens": 28604.0 }, { "bucket": 7224.0, "duration_ms": 9958.172716, "eligible_miss": 0.0, "miss": 4.0, "model": 338.0, "overflow": 4.0, "padding": 12.0, "tokens": 27768.0 }, { "bucket": 7200.0, "duration_ms": 9997.393850000006, "eligible_miss": 0.0, "miss": 4.0, "model": 311.0, "overflow": 4.0, "padding": 8.0, "tokens": 27763.0 }, { "bucket": 7376.0, "duration_ms": 9988.796274000002, "eligible_miss": 0.0, "miss": 4.0, "model": 292.0, "overflow": 4.0, "padding": 12.0, "tokens": 27948.0 }, { "bucket": 7464.0, "duration_ms": 9971.854588999997, "eligible_miss": 0.0, "miss": 4.0, "model": 292.0, "overflow": 4.0, "padding": 5.0, "tokens": 28047.0 }, { "bucket": 7280.0, "duration_ms": 9992.991605999998, "eligible_miss": 0.0, "miss": 4.0, "model": 276.0, "overflow": 4.0, "padding": 8.0, "tokens": 27860.0 }, { "bucket": 7888.0, "duration_ms": 10047.721750999994, "eligible_miss": 0.0, "miss": 4.0, "model": 289.0, "overflow": 4.0, "padding": 12.0, "tokens": 28460.0 }, { "bucket": 8672.0, "duration_ms": 10296.579270999995, "eligible_miss": 0.0, "miss": 4.0, "model": 330.0, "overflow": 4.0, "padding": 12.0, "tokens": 29248.0 }, { "bucket": 7912.0, "duration_ms": 10413.904203, "eligible_miss": 0.0, "miss": 4.0, "model": 320.0, "overflow": 4.0, "padding": 8.0, "tokens": 28492.0 }, { "bucket": 7792.0, "duration_ms": 9163.911243, "eligible_miss": 0.0, "miss": 2.0, "model": 309.0, "overflow": 2.0, "padding": 12.0, "tokens": 18074.0 } ], "clean": { "admitted": 736, "completed": 736, "completed_throughput_rps": 3.066666666666667, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 942080, "offered_rps": 3.066666666666667, "output_tokens": 376832, "start_s": 60.0 }, "config": "C00", "drain_quarantined": false, "drain_seconds": 5.035221696016379, "latency_s": { "e2e": { "mean": 8.60263692463037, "n": 736, "p50": 8.720922641005018, "p95": 9.229017912512063, "p99": 9.427626249768945 }, "tpot": { "mean": 0.015932894322490253, "n": 736, "p50": 0.016117811239738683, "p95": 0.01720207957583063, "p99": 0.017540519277731717 }, "ttft": { "mean": 0.4609279258378513, "n": 736, "p50": 0.4356144489865983, "p95": 0.554922532508499, "p99": 0.5631193216860991 } }, "layer1": { "decode_tokens": 375768, "kv_usage_max": 0.17042443903757776, "kv_usage_mean": 0.13114972391662066, "mode_counts": { "FULL": 14817, "NONE": 186 }, "mode_shares": { "FULL": 0.9876024795040992, "NONE": 0.012397520495900819 }, "preemptions": 0, "prefill_tokens": 942080, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 1, "queue_waiting_mean": 0.005398920215956809, "records_all": 22882, "records_clean": 15003, "requests_per_step": { "mean": 25.100779844031194, "n": 15003, "p50": 24.0, "p95": 32.0, "p99": 32.0 }, "scheduled_tokens_per_step": { "mean": 87.83896554022529, "n": 15003, "p50": 24.0, "p95": 32.0, "p99": 2102.0 }, "step_duration_ms": { "mean": 31.925929198826903, "n": 15003, "p50": 25.808318, "p95": 29.5452691, "p99": 412.22777862000004 }, "token_efficiency_per_ms": 2.7513362255859692 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P07", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 3.2, "clean_c_waiting_median": 0.0, "completion_rate_rps": 2.4, "completion_rate_within_10pct": false, "tail_end_s": 331.94992835301673, "tail_start_s": 321.94992835301673, "valid": false, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 3.2, "clean_c_waiting_median": 0.0, "completion_rate_rps": 3.2, "completion_rate_within_10pct": true, "tail_end_s": 364.21091389100184, "tail_start_s": 354.21091389100184, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 736, "run_dir": "runs/phase3/primary/P07-C00/moderate", "run_id": "P07-C00-moderate", "trace_files": 2, "waste": { "R128": 0.0, "R32": 0.0, "R64": 0.0, "bucket_slack": 0.0014049177504090948, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.012397520495900819, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 186, "moe_layer_cv": null, "overflow_rate": 0.012397520495900819, "padded_tokens_per_useful_token": 0.00039610030898859353, "padding_fraction": 0.0014049177504090948 } }, "P07-C00-saturation": { "blocks": [ { "bucket": 16752.0, "duration_ms": 9950.153387999995, "eligible_miss": 0.0, "miss": 12.0, "model": 99.0, "overflow": 12.0, "padding": 325.0, "tokens": 31732.0 }, { "bucket": 15208.0, "duration_ms": 9991.850533, "eligible_miss": 0.0, "miss": 13.0, "model": 96.0, "overflow": 13.0, "padding": 289.0, "tokens": 33555.0 }, { "bucket": 14240.0, "duration_ms": 10002.270118999997, "eligible_miss": 0.0, "miss": 15.0, "model": 96.0, "overflow": 15.0, "padding": 297.0, "tokens": 33650.0 }, { "bucket": 1040.0, "duration_ms": 11075.8932, "eligible_miss": 0.0, "miss": 14.0, "model": 20.0, "overflow": 14.0, "padding": 30.0, "tokens": 106042.0 }, { "duration_ms": 10086.661052, "eligible_miss": 0.0, "miss": 12.0, "model": 12.0, "overflow": 12.0, "tokens": 98304.0 }, { "bucket": 2696.0, "duration_ms": 8805.740211999997, "eligible_miss": 0.0, "miss": 9.0, "model": 21.0, "overflow": 9.0, "padding": 12.0, "tokens": 74012.0 }, { "bucket": 24512.0, "duration_ms": 9992.72727, "eligible_miss": 0.0, "miss": 1.0, "model": 114.0, "overflow": 1.0, "padding": 386.0, "tokens": 25608.0 }, { "bucket": 23256.0, "duration_ms": 10053.696391000003, "eligible_miss": 0.0, "miss": 1.0, "model": 117.0, "overflow": 1.0, "padding": 406.0, "tokens": 24716.0 }, { "bucket": 20208.0, "duration_ms": 9956.686812000004, "eligible_miss": 0.0, "miss": 4.0, "model": 112.0, "overflow": 4.0, "padding": 432.0, "tokens": 25111.0 }, { "bucket": 19280.0, "duration_ms": 9997.674086, "eligible_miss": 0.0, "miss": 5.0, "model": 112.0, "overflow": 5.0, "padding": 349.0, "tokens": 25614.0 }, { "bucket": 1984.0, "duration_ms": 10921.154089999998, "eligible_miss": 0.0, "miss": 13.0, "model": 24.0, "overflow": 13.0, "padding": 31.0, "tokens": 100985.0 }, { "duration_ms": 10088.02937, "eligible_miss": 0.0, "miss": 12.0, "model": 12.0, "overflow": 12.0, "tokens": 98304.0 }, { "duration_ms": 10118.796231, "eligible_miss": 0.0, "miss": 12.0, "model": 12.0, "overflow": 12.0, "tokens": 98304.0 }, { "bucket": 20336.0, "duration_ms": 8830.944203000001, "eligible_miss": 0.0, "miss": 2.0, "model": 96.0, "overflow": 2.0, "padding": 322.0, "tokens": 22057.0 }, { "bucket": 19904.0, "duration_ms": 10019.577912999996, "eligible_miss": 0.0, "miss": 7.0, "model": 105.0, "overflow": 7.0, "padding": 396.0, "tokens": 30394.0 }, { "bucket": 17688.0, "duration_ms": 9972.803946999999, "eligible_miss": 0.0, "miss": 11.0, "model": 104.0, "overflow": 11.0, "padding": 272.0, "tokens": 29529.0 }, { "bucket": 15184.0, "duration_ms": 9973.274595999994, "eligible_miss": 0.0, "miss": 13.0, "model": 97.0, "overflow": 13.0, "padding": 273.0, "tokens": 33543.0 }, { "bucket": 12312.0, "duration_ms": 10407.001862, "eligible_miss": 0.0, "miss": 15.0, "model": 86.0, "overflow": 15.0, "padding": 265.0, "tokens": 51277.0 }, { "duration_ms": 10120.670290999999, "eligible_miss": 0.0, "miss": 12.0, "model": 12.0, "overflow": 12.0, "tokens": 98304.0 }, { "duration_ms": 10056.795141, "eligible_miss": 0.0, "miss": 12.0, "model": 12.0, "overflow": 12.0, "tokens": 98304.0 }, { "bucket": 7392.0, "duration_ms": 9387.771273, "eligible_miss": 0.0, "miss": 8.0, "model": 41.0, "overflow": 8.0, "padding": 85.0, "tokens": 65871.0 }, { "bucket": 24560.0, "duration_ms": 10008.093556999993, "eligible_miss": 0.0, "miss": 1.0, "model": 116.0, "overflow": 1.0, "padding": 433.0, "tokens": 24978.0 }, { "bucket": 21704.0, "duration_ms": 9986.943306, "eligible_miss": 0.0, "miss": 3.0, "model": 113.0, "overflow": 3.0, "padding": 350.0, "tokens": 25656.0 }, { "bucket": 20592.0, "duration_ms": 10009.293340000002, "eligible_miss": 0.0, "miss": 3.0, "model": 113.0, "overflow": 3.0, "padding": 404.0, "tokens": 25315.0 }, { "bucket": 16872.0, "duration_ms": 9990.23609, "eligible_miss": 0.0, "miss": 9.0, "model": 103.0, "overflow": 9.0, "padding": 297.0, "tokens": 29596.0 }, { "duration_ms": 10501.451498, "eligible_miss": 0.0, "miss": 14.0, "model": 14.0, "overflow": 14.0, "tokens": 103534.0 }, { "duration_ms": 10057.099084000001, "eligible_miss": 0.0, "miss": 12.0, "model": 12.0, "overflow": 12.0, "tokens": 98304.0 }, { "bucket": 224.0, "duration_ms": 9523.209128, "eligible_miss": 0.0, "miss": 11.0, "model": 12.0, "overflow": 11.0, "padding": 4.0, "tokens": 87906.0 }, { "bucket": 23048.0, "duration_ms": 9911.289427, "eligible_miss": 0.0, "miss": 3.0, "model": 110.0, "overflow": 3.0, "padding": 364.0, "tokens": 26660.0 }, { "bucket": 19912.0, "duration_ms": 9967.263191999999, "eligible_miss": 0.0, "miss": 8.0, "model": 107.0, "overflow": 8.0, "padding": 367.0, "tokens": 27474.0 }, { "bucket": 18392.0, "duration_ms": 9988.550586000003, "eligible_miss": 0.0, "miss": 9.0, "model": 105.0, "overflow": 9.0, "padding": 302.0, "tokens": 28252.0 }, { "bucket": 15400.0, "duration_ms": 9924.671659000003, "eligible_miss": 0.0, "miss": 13.0, "model": 99.0, "overflow": 13.0, "padding": 300.0, "tokens": 30650.0 }, { "bucket": 9304.0, "duration_ms": 10994.186665000001, "eligible_miss": 0.0, "miss": 14.0, "model": 68.0, "overflow": 14.0, "padding": 198.0, "tokens": 70027.0 }, { "duration_ms": 10127.156386, "eligible_miss": 0.0, "miss": 12.0, "model": 12.0, "overflow": 12.0, "tokens": 98304.0 }, { "duration_ms": 10078.856573000001, "eligible_miss": 0.0, "miss": 12.0, "model": 12.0, "overflow": 12.0, "tokens": 98304.0 }, { "bucket": 11384.0, "duration_ms": 8814.812563000001, "eligible_miss": 0.0, "miss": 6.0, "model": 57.0, "overflow": 6.0, "padding": 170.0, "tokens": 48368.0 }, { "bucket": 23984.0, "duration_ms": 10032.058657000003, "eligible_miss": 0.0, "miss": 1.0, "model": 115.0, "overflow": 1.0, "padding": 384.0, "tokens": 25458.0 }, { "bucket": 21704.0, "duration_ms": 9986.41377, "eligible_miss": 0.0, "miss": 3.0, "model": 114.0, "overflow": 3.0, "padding": 418.0, "tokens": 24611.0 }, { "bucket": 20344.0, "duration_ms": 9950.299295000006, "eligible_miss": 0.0, "miss": 3.0, "model": 112.0, "overflow": 3.0, "padding": 324.0, "tokens": 25289.0 }, { "bucket": 13440.0, "duration_ms": 10610.674172999996, "eligible_miss": 0.0, "miss": 13.0, "model": 90.0, "overflow": 13.0, "padding": 266.0, "tokens": 50097.0 }, { "duration_ms": 10146.211426, "eligible_miss": 0.0, "miss": 12.0, "model": 12.0, "overflow": 12.0, "tokens": 98304.0 }, { "duration_ms": 10060.054723, "eligible_miss": 0.0, "miss": 12.0, "model": 12.0, "overflow": 12.0, "tokens": 98304.0 }, { "bucket": 3584.0, "duration_ms": 9127.613545, "eligible_miss": 0.0, "miss": 9.0, "model": 25.0, "overflow": 9.0, "padding": 67.0, "tokens": 74197.0 }, { "bucket": 23472.0, "duration_ms": 9983.624336, "eligible_miss": 0.0, "miss": 2.0, "model": 112.0, "overflow": 2.0, "padding": 390.0, "tokens": 25682.0 }, { "bucket": 19264.0, "duration_ms": 10066.432618, "eligible_miss": 0.0, "miss": 8.0, "model": 105.0, "overflow": 8.0, "padding": 305.0, "tokens": 30308.0 }, { "bucket": 17736.0, "duration_ms": 10044.883365000007, "eligible_miss": 0.0, "miss": 10.0, "model": 103.0, "overflow": 10.0, "padding": 331.0, "tokens": 30141.0 }, { "bucket": 15312.0, "duration_ms": 10041.116643000001, "eligible_miss": 0.0, "miss": 13.0, "model": 99.0, "overflow": 13.0, "padding": 314.0, "tokens": 31613.0 }, { "bucket": 7192.0, "duration_ms": 10456.028967, "eligible_miss": 0.0, "miss": 14.0, "model": 56.0, "overflow": 14.0, "padding": 129.0, "tokens": 72857.0 } ], "clean": { "admitted": 1226, "completed": 1226, "completed_throughput_rps": 5.108333333333333, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 1569280, "offered_rps": 5.108333333333333, "output_tokens": 627712, "start_s": 60.0 }, "config": "C00", "drain_quarantined": false, "drain_seconds": 26.098238860984566, "latency_s": { "e2e": { "mean": 50.88784179576417, "n": 1226, "p50": 42.76737600599881, "p95": 66.36966083350853, "p99": 76.04152522151708 }, "tpot": { "mean": 0.07373855953213852, "n": 1226, "p50": 0.06754604706850764, "p95": 0.11021927271477756, "p99": 0.11510430237866912 }, "ttft": { "mean": 13.207437874841386, "n": 1226, "p50": 7.195238005995634, "p95": 31.643819290002284, "p99": 41.397227533998375 } }, "layer1": { "decode_tokens": 1086437, "kv_usage_max": 1.0, "kv_usage_mean": 0.9898433722094666, "mode_counts": { "FULL": 2964, "NONE": 433, "PIECEWISE": 11 }, "mode_shares": { "FULL": 0.8697183098591549, "NONE": 0.12705399061032863, "PIECEWISE": 0.003227699530516432 }, "preemptions": 391, "prefill_tokens": 1528968, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 91, "queue_waiting_mean": 66.81338028169014, "records_all": 5714, "records_clean": 3408, "requests_per_step": { "mean": 188.46537558685446, "n": 3408, "p50": 186.5, "p95": 218.0, "p99": 223.0 }, "scheduled_tokens_per_step": { "mean": 767.431044600939, "n": 3408, "p50": 192.0, "p95": 8192.0, "p99": 8192.0 }, "step_duration_ms": { "mean": 140.90337340140846, "n": 3408, "p50": 84.995821, "p95": 838.4765309999999, "p99": 847.72110561 }, "token_efficiency_per_ms": 5.44650582931514 }, "layer2_missing_after_controller_cleanup": true, "load": "saturation", "pattern": "P07", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 4.05, "clean_c_waiting_median": 70.0, "completion_rate_rps": 8.3, "completion_rate_within_10pct": false, "tail_end_s": 358.0940292410087, "tail_start_s": 348.0940292410087, "valid": false, "waiting_median": 85.0, "waiting_within_10pct": false, "window": 1 }, { "clean_c_completion_rate_median_rps": 4.05, "clean_c_waiting_median": 70.0, "completion_rate_rps": 8.8, "completion_rate_within_10pct": false, "tail_end_s": 417.66287675101194, "tail_start_s": 407.66287675101194, "valid": false, "waiting_median": 85.0, "waiting_within_10pct": false, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 1226, "run_dir": "runs/phase3/primary/P07-C00/saturation", "run_id": "P07-C00-saturation", "trace_files": 0, "waste": { "R128": 0.0, "R32": 0.0, "R64": 0.0, "bucket_slack": 0.017754083421928288, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.12705399061032863, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.12705399061032863, "padded_tokens_per_useful_token": 0.003933234049793436, "padding_fraction": 0.017754083421928288 } }, "P08-C00-moderate": { "blocks": [ { "bucket": 14056.0, "duration_ms": 9973.848525000003, "eligible_miss": 0.0, "miss": 4.0, "model": 263.0, "overflow": 4.0, "padding": 0.0, "tokens": 22440.0 }, { "bucket": 14216.0, "duration_ms": 9967.381556999999, "eligible_miss": 0.0, "miss": 3.0, "model": 265.0, "overflow": 3.0, "padding": 0.0, "tokens": 20504.0 }, { "bucket": 13688.0, "duration_ms": 9966.267621999996, "eligible_miss": 0.0, "miss": 4.0, "model": 257.0, "overflow": 4.0, "padding": 0.0, "tokens": 22072.0 }, { "bucket": 14104.0, "duration_ms": 9990.000707, "eligible_miss": 0.0, "miss": 3.0, "model": 259.0, "overflow": 3.0, "padding": 0.0, "tokens": 20392.0 }, { "bucket": 13912.0, "duration_ms": 9988.124715999998, "eligible_miss": 0.0, "miss": 4.0, "model": 254.0, "overflow": 4.0, "padding": 0.0, "tokens": 22296.0 }, { "bucket": 14400.0, "duration_ms": 9978.191433, "eligible_miss": 0.0, "miss": 4.0, "model": 263.0, "overflow": 4.0, "padding": 0.0, "tokens": 20738.0 }, { "bucket": 14136.0, "duration_ms": 9975.772872000003, "eligible_miss": 0.0, "miss": 6.0, "model": 265.0, "overflow": 6.0, "padding": 0.0, "tokens": 22621.0 }, { "bucket": 15152.0, "duration_ms": 9957.495739999998, "eligible_miss": 0.0, "miss": 3.0, "model": 290.0, "overflow": 3.0, "padding": 4.0, "tokens": 21436.0 }, { "bucket": 13672.0, "duration_ms": 10003.284594000004, "eligible_miss": 0.0, "miss": 4.0, "model": 274.0, "overflow": 4.0, "padding": 3.0, "tokens": 22053.0 }, { "bucket": 13912.0, "duration_ms": 9952.839312, "eligible_miss": 0.0, "miss": 3.0, "model": 274.0, "overflow": 3.0, "padding": 0.0, "tokens": 20200.0 }, { "bucket": 13656.0, "duration_ms": 9985.693855000003, "eligible_miss": 0.0, "miss": 4.0, "model": 264.0, "overflow": 4.0, "padding": 0.0, "tokens": 22040.0 }, { "bucket": 14016.0, "duration_ms": 9984.229559999998, "eligible_miss": 0.0, "miss": 3.0, "model": 263.0, "overflow": 3.0, "padding": 0.0, "tokens": 20304.0 }, { "bucket": 13808.0, "duration_ms": 10000.379454999997, "eligible_miss": 0.0, "miss": 4.0, "model": 258.0, "overflow": 4.0, "padding": 0.0, "tokens": 22192.0 }, { "bucket": 14400.0, "duration_ms": 9949.354869000004, "eligible_miss": 0.0, "miss": 3.0, "model": 264.0, "overflow": 3.0, "padding": 0.0, "tokens": 20688.0 }, { "bucket": 14200.0, "duration_ms": 9995.867115, "eligible_miss": 0.0, "miss": 5.0, "model": 267.0, "overflow": 5.0, "padding": 0.0, "tokens": 22635.0 }, { "bucket": 15216.0, "duration_ms": 9971.602727000003, "eligible_miss": 0.0, "miss": 3.0, "model": 288.0, "overflow": 3.0, "padding": 12.0, "tokens": 21236.0 }, { "bucket": 13944.0, "duration_ms": 9976.335151999996, "eligible_miss": 0.0, "miss": 4.0, "model": 281.0, "overflow": 4.0, "padding": 0.0, "tokens": 22328.0 }, { "bucket": 14112.0, "duration_ms": 9982.280347, "eligible_miss": 0.0, "miss": 3.0, "model": 282.0, "overflow": 3.0, "padding": 7.0, "tokens": 20393.0 }, { "bucket": 13624.0, "duration_ms": 9981.804391, "eligible_miss": 0.0, "miss": 4.0, "model": 272.0, "overflow": 4.0, "padding": 0.0, "tokens": 22008.0 }, { "bucket": 14528.0, "duration_ms": 9978.589668999997, "eligible_miss": 0.0, "miss": 3.0, "model": 282.0, "overflow": 3.0, "padding": 0.0, "tokens": 20816.0 }, { "bucket": 14176.0, "duration_ms": 9974.379933999997, "eligible_miss": 0.0, "miss": 4.0, "model": 284.0, "overflow": 4.0, "padding": 0.0, "tokens": 22560.0 }, { "bucket": 14168.0, "duration_ms": 9961.784644000003, "eligible_miss": 0.0, "miss": 3.0, "model": 285.0, "overflow": 3.0, "padding": 0.0, "tokens": 20456.0 }, { "bucket": 13720.0, "duration_ms": 9975.473181, "eligible_miss": 0.0, "miss": 4.0, "model": 277.0, "overflow": 4.0, "padding": 0.0, "tokens": 22104.0 }, { "bucket": 14168.0, "duration_ms": 9993.255385, "eligible_miss": 0.0, "miss": 4.0, "model": 280.0, "overflow": 4.0, "padding": 0.0, "tokens": 20506.0 }, { "bucket": 13760.0, "duration_ms": 10024.908194000003, "eligible_miss": 0.0, "miss": 4.0, "model": 273.0, "overflow": 4.0, "padding": 0.0, "tokens": 22144.0 }, { "bucket": 14544.0, "duration_ms": 9930.993723000005, "eligible_miss": 0.0, "miss": 4.0, "model": 283.0, "overflow": 4.0, "padding": 2.0, "tokens": 20880.0 }, { "bucket": 14088.0, "duration_ms": 10068.104888999997, "eligible_miss": 0.0, "miss": 5.0, "model": 285.0, "overflow": 5.0, "padding": 0.0, "tokens": 22522.0 }, { "bucket": 14128.0, "duration_ms": 9882.121841999988, "eligible_miss": 0.0, "miss": 3.0, "model": 284.0, "overflow": 3.0, "padding": 4.0, "tokens": 20412.0 }, { "bucket": 13616.0, "duration_ms": 10159.141668999995, "eligible_miss": 0.0, "miss": 4.0, "model": 273.0, "overflow": 4.0, "padding": 0.0, "tokens": 22000.0 }, { "bucket": 13832.0, "duration_ms": 9816.491638000003, "eligible_miss": 0.0, "miss": 3.0, "model": 263.0, "overflow": 3.0, "padding": 0.0, "tokens": 20120.0 }, { "bucket": 13952.0, "duration_ms": 10078.082938999993, "eligible_miss": 0.0, "miss": 4.0, "model": 266.0, "overflow": 4.0, "padding": 0.0, "tokens": 22336.0 }, { "bucket": 13728.0, "duration_ms": 9864.037892999986, "eligible_miss": 0.0, "miss": 3.0, "model": 254.0, "overflow": 3.0, "padding": 0.0, "tokens": 20016.0 }, { "bucket": 14008.0, "duration_ms": 9994.704993000005, "eligible_miss": 0.0, "miss": 3.0, "model": 255.0, "overflow": 3.0, "padding": 0.0, "tokens": 20296.0 }, { "bucket": 13704.0, "duration_ms": 9969.414991000005, "eligible_miss": 0.0, "miss": 4.0, "model": 247.0, "overflow": 4.0, "padding": 0.0, "tokens": 22120.0 }, { "bucket": 14040.0, "duration_ms": 9992.463381999996, "eligible_miss": 0.0, "miss": 3.0, "model": 249.0, "overflow": 3.0, "padding": 0.0, "tokens": 20352.0 }, { "bucket": 14536.0, "duration_ms": 9982.517607999996, "eligible_miss": 0.0, "miss": 4.0, "model": 257.0, "overflow": 4.0, "padding": 0.0, "tokens": 22952.0 }, { "bucket": 15968.0, "duration_ms": 9962.079757999993, "eligible_miss": 0.0, "miss": 3.0, "model": 301.0, "overflow": 3.0, "padding": 0.0, "tokens": 22256.0 }, { "bucket": 14504.0, "duration_ms": 9986.519805000002, "eligible_miss": 0.0, "miss": 4.0, "model": 304.0, "overflow": 4.0, "padding": 0.0, "tokens": 22872.0 }, { "bucket": 13800.0, "duration_ms": 9982.44843, "eligible_miss": 0.0, "miss": 3.0, "model": 298.0, "overflow": 3.0, "padding": 0.0, "tokens": 20064.0 }, { "bucket": 13528.0, "duration_ms": 9954.52768, "eligible_miss": 0.0, "miss": 4.0, "model": 282.0, "overflow": 4.0, "padding": 0.0, "tokens": 21904.0 }, { "bucket": 13584.0, "duration_ms": 9994.419997000003, "eligible_miss": 0.0, "miss": 3.0, "model": 274.0, "overflow": 3.0, "padding": 0.0, "tokens": 19872.0 }, { "bucket": 13288.0, "duration_ms": 9966.098695, "eligible_miss": 0.0, "miss": 4.0, "model": 255.0, "overflow": 4.0, "padding": 0.0, "tokens": 21672.0 }, { "bucket": 15040.0, "duration_ms": 9972.185662000004, "eligible_miss": 0.0, "miss": 3.0, "model": 282.0, "overflow": 3.0, "padding": 0.0, "tokens": 21328.0 }, { "bucket": 14256.0, "duration_ms": 10008.302290000003, "eligible_miss": 0.0, "miss": 4.0, "model": 277.0, "overflow": 4.0, "padding": 0.0, "tokens": 22640.0 }, { "bucket": 13504.0, "duration_ms": 9971.076230000006, "eligible_miss": 0.0, "miss": 4.0, "model": 268.0, "overflow": 4.0, "padding": 0.0, "tokens": 19842.0 }, { "bucket": 13720.0, "duration_ms": 9979.042713999997, "eligible_miss": 0.0, "miss": 4.0, "model": 261.0, "overflow": 4.0, "padding": 0.0, "tokens": 22104.0 }, { "bucket": 14888.0, "duration_ms": 9956.323997, "eligible_miss": 0.0, "miss": 3.0, "model": 282.0, "overflow": 3.0, "padding": 2.0, "tokens": 21174.0 }, { "bucket": 13376.0, "duration_ms": 9991.657548999998, "eligible_miss": 0.0, "miss": 5.0, "model": 260.0, "overflow": 5.0, "padding": 0.0, "tokens": 21810.0 } ], "clean": { "admitted": 1344, "completed": 1344, "completed_throughput_rps": 5.6, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 1720320, "offered_rps": 5.6, "output_tokens": 688128, "start_s": 60.0 }, "config": "C00", "drain_quarantined": false, "drain_seconds": 5.560244205989875, "latency_s": { "e2e": { "mean": 9.539366701375652, "n": 1344, "p50": 9.522452891003923, "p95": 10.283733322568878, "p99": 10.47988052393106 }, "tpot": { "mean": 0.018335971554982657, "n": 1344, "p50": 0.0183028954266283, "p95": 0.019802372696771993, "p99": 0.020153929372081728 }, "ttft": { "mean": 0.16968523677951453, "n": 1344, "p50": 0.1693532774952473, "p95": 0.1819040500369738, "p99": 0.19063215127098374 } }, "layer1": { "decode_tokens": 684642, "kv_usage_max": 0.14144363341443633, "kv_usage_mean": 0.12019157982892181, "mode_counts": { "FULL": 12866, "NONE": 177, "PIECEWISE": 1 }, "mode_shares": { "FULL": 0.9863538791781662, "NONE": 0.013569457221711132, "PIECEWISE": 7.666360012266176e-05 }, "preemptions": 0, "prefill_tokens": 344064, "prefix_query_hit_ratio": 0.8, "queue_waiting_max": 0, "queue_waiting_mean": 0.0, "records_all": 19842, "records_clean": 13044, "requests_per_step": { "mean": 52.59015639374425, "n": 13044, "p50": 56.0, "p95": 56.0, "p99": 56.0 }, "scheduled_tokens_per_step": { "mean": 78.8643054277829, "n": 13044, "p50": 56.0, "p95": 56.0, "p99": 2096.0 }, "step_duration_ms": { "mean": 36.71817724087703, "n": 13044, "p50": 33.9972625, "p95": 37.57236414999999, "p99": 144.8586379 }, "token_efficiency_per_ms": 2.147827352932598 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P08", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 5.6, "clean_c_waiting_median": 0.0, "completion_rate_rps": 7.2, "completion_rate_within_10pct": false, "tail_end_s": 332.508747830987, "tail_start_s": 322.508747830987, "valid": false, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 5.6, "clean_c_waiting_median": 0.0, "completion_rate_rps": 5.6, "completion_rate_within_10pct": true, "tail_end_s": 365.04628598099225, "tail_start_s": 355.04628598099225, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 1344, "run_dir": "runs/phase3/primary/P08-C00/moderate", "run_id": "P08-C00-moderate", "trace_files": 2, "waste": { "R128": 0.0, "R32": 0.0, "R64": 0.0, "bucket_slack": 5.026789832874023e-05, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.013569457221711132, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 178, "moe_layer_cv": null, "overflow_rate": 0.013569457221711132, "padded_tokens_per_useful_token": 3.3051231352786896e-05, "padding_fraction": 5.026789832874023e-05 } }, "P08-C00-saturation": { "blocks": [ { "bucket": 9216.0, "duration_ms": 9340.304726, "eligible_miss": 0.0, "miss": 7.0, "model": 43.0, "overflow": 7.0, "padding": 0.0, "tokens": 62688.0 }, { "bucket": 26624.0, "duration_ms": 10001.778646000006, "eligible_miss": 0.0, "miss": 0.0, "model": 104.0, "overflow": 0.0, "padding": 0.0, "tokens": 26624.0 }, { "bucket": 25344.0, "duration_ms": 9956.614504999998, "eligible_miss": 0.0, "miss": 0.0, "model": 99.0, "overflow": 0.0, "padding": 0.0, "tokens": 25344.0 }, { "bucket": 24832.0, "duration_ms": 10030.431760000001, "eligible_miss": 0.0, "miss": 0.0, "model": 97.0, "overflow": 0.0, "padding": 0.0, "tokens": 24832.0 }, { "bucket": 24064.0, "duration_ms": 9933.479672999998, "eligible_miss": 0.0, "miss": 0.0, "model": 94.0, "overflow": 0.0, "padding": 0.0, "tokens": 24064.0 }, { "bucket": 19160.0, "duration_ms": 10748.071276, "eligible_miss": 0.0, "miss": 5.0, "model": 79.0, "overflow": 5.0, "padding": 9.0, "tokens": 45939.0 }, { "bucket": 12288.0, "duration_ms": 9267.026669000006, "eligible_miss": 0.0, "miss": 5.0, "model": 53.0, "overflow": 5.0, "padding": 0.0, "tokens": 52621.0 }, { "bucket": 26368.0, "duration_ms": 9943.246027999998, "eligible_miss": 0.0, "miss": 0.0, "model": 103.0, "overflow": 0.0, "padding": 0.0, "tokens": 26368.0 }, { "bucket": 25856.0, "duration_ms": 10050.698422000001, "eligible_miss": 0.0, "miss": 0.0, "model": 101.0, "overflow": 0.0, "padding": 0.0, "tokens": 25856.0 }, { "bucket": 24832.0, "duration_ms": 9989.595579000003, "eligible_miss": 0.0, "miss": 0.0, "model": 97.0, "overflow": 0.0, "padding": 0.0, "tokens": 24832.0 }, { "bucket": 24064.0, "duration_ms": 9906.974473999995, "eligible_miss": 0.0, "miss": 0.0, "model": 94.0, "overflow": 0.0, "padding": 0.0, "tokens": 24064.0 }, { "bucket": 15832.0, "duration_ms": 11031.223406, "eligible_miss": 0.0, "miss": 7.0, "model": 68.0, "overflow": 7.0, "padding": 9.0, "tokens": 58554.0 }, { "bucket": 16128.0, "duration_ms": 8962.881495000001, "eligible_miss": 0.0, "miss": 3.0, "model": 66.0, "overflow": 3.0, "padding": 0.0, "tokens": 40518.0 }, { "bucket": 26368.0, "duration_ms": 10047.384447999999, "eligible_miss": 0.0, "miss": 0.0, "model": 103.0, "overflow": 0.0, "padding": 0.0, "tokens": 26368.0 }, { "bucket": 25344.0, "duration_ms": 9939.983968000004, "eligible_miss": 0.0, "miss": 0.0, "model": 99.0, "overflow": 0.0, "padding": 0.0, "tokens": 25344.0 }, { "bucket": 24576.0, "duration_ms": 9980.957590000002, "eligible_miss": 0.0, "miss": 0.0, "model": 96.0, "overflow": 0.0, "padding": 0.0, "tokens": 24576.0 }, { "bucket": 24064.0, "duration_ms": 10063.673846999998, "eligible_miss": 0.0, "miss": 0.0, "model": 94.0, "overflow": 0.0, "padding": 0.0, "tokens": 24064.0 }, { "bucket": 12760.0, "duration_ms": 10636.981154, "eligible_miss": 0.0, "miss": 8.0, "model": 57.0, "overflow": 8.0, "padding": 9.0, "tokens": 63581.0 }, { "bucket": 19200.0, "duration_ms": 9239.554301999997, "eligible_miss": 0.0, "miss": 2.0, "model": 77.0, "overflow": 2.0, "padding": 0.0, "tokens": 35491.0 }, { "bucket": 26368.0, "duration_ms": 10018.135894000001, "eligible_miss": 0.0, "miss": 0.0, "model": 103.0, "overflow": 0.0, "padding": 0.0, "tokens": 26368.0 }, { "bucket": 25600.0, "duration_ms": 10004.704074, "eligible_miss": 0.0, "miss": 0.0, "model": 100.0, "overflow": 0.0, "padding": 0.0, "tokens": 25600.0 }, { "bucket": 24832.0, "duration_ms": 9988.921407000002, "eligible_miss": 0.0, "miss": 0.0, "model": 97.0, "overflow": 0.0, "padding": 0.0, "tokens": 24832.0 }, { "bucket": 24064.0, "duration_ms": 9980.550060999996, "eligible_miss": 0.0, "miss": 0.0, "model": 94.0, "overflow": 0.0, "padding": 0.0, "tokens": 24064.0 }, { "bucket": 9176.0, "duration_ms": 10845.426534999999, "eligible_miss": 0.0, "miss": 10.0, "model": 45.0, "overflow": 10.0, "padding": 9.0, "tokens": 76288.0 }, { "bucket": 23552.0, "duration_ms": 9122.136448, "eligible_miss": 0.0, "miss": 0.0, "model": 92.0, "overflow": 0.0, "padding": 0.0, "tokens": 23552.0 }, { "bucket": 26112.0, "duration_ms": 10039.638599000002, "eligible_miss": 0.0, "miss": 0.0, "model": 102.0, "overflow": 0.0, "padding": 0.0, "tokens": 26112.0 }, { "bucket": 25088.0, "duration_ms": 9935.394242, "eligible_miss": 0.0, "miss": 0.0, "model": 98.0, "overflow": 0.0, "padding": 0.0, "tokens": 25088.0 }, { "bucket": 24576.0, "duration_ms": 9981.978842999999, "eligible_miss": 0.0, "miss": 0.0, "model": 96.0, "overflow": 0.0, "padding": 0.0, "tokens": 24576.0 }, { "bucket": 24064.0, "duration_ms": 10074.602884000005, "eligible_miss": 0.0, "miss": 0.0, "model": 94.0, "overflow": 0.0, "padding": 0.0, "tokens": 24064.0 }, { "bucket": 6104.0, "duration_ms": 9997.324195000001, "eligible_miss": 0.0, "miss": 10.0, "model": 33.0, "overflow": 10.0, "padding": 9.0, "tokens": 73216.0 }, { "bucket": 26880.0, "duration_ms": 9919.636349999999, "eligible_miss": 0.0, "miss": 0.0, "model": 105.0, "overflow": 0.0, "padding": 0.0, "tokens": 26880.0 }, { "bucket": 26112.0, "duration_ms": 10016.483458, "eligible_miss": 0.0, "miss": 0.0, "model": 102.0, "overflow": 0.0, "padding": 0.0, "tokens": 26112.0 }, { "bucket": 25344.0, "duration_ms": 9973.412112000004, "eligible_miss": 0.0, "miss": 0.0, "model": 99.0, "overflow": 0.0, "padding": 0.0, "tokens": 25344.0 }, { "bucket": 24832.0, "duration_ms": 10002.756156, "eligible_miss": 0.0, "miss": 0.0, "model": 97.0, "overflow": 0.0, "padding": 0.0, "tokens": 24832.0 }, { "bucket": 24064.0, "duration_ms": 9929.880055000001, "eligible_miss": 0.0, "miss": 0.0, "model": 94.0, "overflow": 0.0, "padding": 0.0, "tokens": 24064.0 }, { "bucket": 6872.0, "duration_ms": 10052.947775999999, "eligible_miss": 0.0, "miss": 10.0, "model": 36.0, "overflow": 10.0, "padding": 9.0, "tokens": 73984.0 }, { "bucket": 26624.0, "duration_ms": 9946.62487499999, "eligible_miss": 0.0, "miss": 0.0, "model": 104.0, "overflow": 0.0, "padding": 0.0, "tokens": 26624.0 }, { "bucket": 25600.0, "duration_ms": 9982.362614000001, "eligible_miss": 0.0, "miss": 0.0, "model": 100.0, "overflow": 0.0, "padding": 0.0, "tokens": 25600.0 }, { "bucket": 25088.0, "duration_ms": 10020.922033, "eligible_miss": 0.0, "miss": 0.0, "model": 98.0, "overflow": 0.0, "padding": 0.0, "tokens": 25088.0 }, { "bucket": 24320.0, "duration_ms": 9969.521037, "eligible_miss": 0.0, "miss": 0.0, "model": 95.0, "overflow": 0.0, "padding": 0.0, "tokens": 24320.0 }, { "bucket": 22488.0, "duration_ms": 10837.747847000004, "eligible_miss": 0.0, "miss": 3.0, "model": 90.0, "overflow": 3.0, "padding": 9.0, "tokens": 36127.0 }, { "bucket": 8448.0, "duration_ms": 9141.736970000002, "eligible_miss": 0.0, "miss": 7.0, "model": 40.0, "overflow": 7.0, "padding": 0.0, "tokens": 61921.0 }, { "bucket": 26624.0, "duration_ms": 9981.340275999999, "eligible_miss": 0.0, "miss": 0.0, "model": 104.0, "overflow": 0.0, "padding": 0.0, "tokens": 26624.0 }, { "bucket": 25600.0, "duration_ms": 9997.061726999997, "eligible_miss": 0.0, "miss": 0.0, "model": 100.0, "overflow": 0.0, "padding": 0.0, "tokens": 25600.0 }, { "bucket": 24832.0, "duration_ms": 9999.201582, "eligible_miss": 0.0, "miss": 0.0, "model": 97.0, "overflow": 0.0, "padding": 0.0, "tokens": 24832.0 }, { "bucket": 24320.0, "duration_ms": 10035.232025000005, "eligible_miss": 0.0, "miss": 0.0, "model": 95.0, "overflow": 0.0, "padding": 0.0, "tokens": 24320.0 }, { "bucket": 19416.0, "duration_ms": 10835.279315, "eligible_miss": 0.0, "miss": 5.0, "model": 80.0, "overflow": 5.0, "padding": 9.0, "tokens": 46195.0 }, { "bucket": 11776.0, "duration_ms": 9096.011046000003, "eligible_miss": 0.0, "miss": 5.0, "model": 51.0, "overflow": 5.0, "padding": 0.0, "tokens": 52109.0 } ], "clean": { "admitted": 2233, "completed": 2233, "completed_throughput_rps": 9.304166666666667, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 2858240, "offered_rps": 9.304166666666667, "output_tokens": 1143296, "start_s": 60.0 }, "config": "C00", "drain_quarantined": false, "drain_seconds": 14.923095890000695, "latency_s": { "e2e": { "mean": 29.33866877817903, "n": 2233, "p50": 29.366875634004828, "p95": 29.640699471993138, "p99": 29.840447392413626 }, "tpot": { "mean": 0.055211153321731224, "n": 2233, "p50": 0.05503479847167354, "p95": 0.05621860527475374, "p99": 0.05679465504637017 }, "ttft": { "mean": 1.1257694307743766, "n": 2233, "p50": 1.2680383940169122, "p95": 1.3710993590124416, "p99": 1.7439167306513992 } }, "layer1": { "decode_tokens": 1059552, "kv_usage_max": 0.6920789402541228, "kv_usage_mean": 0.47382357971574685, "mode_counts": { "FULL": 4070, "NONE": 87, "PIECEWISE": 8 }, "mode_shares": { "FULL": 0.9771908763505402, "NONE": 0.020888355342136854, "PIECEWISE": 0.0019207683073229293 }, "preemptions": 0, "prefill_tokens": 576512, "prefix_query_hit_ratio": 0.8, "queue_waiting_max": 0, "queue_waiting_mean": 0.0, "records_all": 8229, "records_clean": 4165, "requests_per_step": { "mean": 254.93517406962786, "n": 4165, "p50": 256.0, "p95": 256.0, "p99": 256.0 }, "scheduled_tokens_per_step": { "mean": 392.8124849939976, "n": 4165, "p50": 256.0, "p95": 256.0, "p99": 8099.0 }, "step_duration_ms": { "mean": 114.95746276206482, "n": 4165, "p50": 101.934486, "p95": 107.8044754, "p99": 858.72215388 }, "token_efficiency_per_ms": 3.4170246589995465 }, "layer2_missing_after_controller_cleanup": true, "load": "saturation", "pattern": "P08", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 0.0, "clean_c_waiting_median": 0.0, "completion_rate_rps": 5.2, "completion_rate_within_10pct": false, "tail_end_s": 411.30330635100836, "tail_start_s": 401.30330635100836, "valid": false, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 0.0, "clean_c_waiting_median": 0.0, "completion_rate_rps": 10.1, "completion_rate_within_10pct": false, "tail_end_s": 493.2576180040196, "tail_start_s": 483.2576180040196, "valid": false, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 2233, "run_dir": "runs/phase3/primary/P08-C00/saturation", "run_id": "P08-C00-saturation", "trace_files": 0, "waste": { "R128": 0.0, "R32": 0.0, "R64": 0.0, "bucket_slack": 6.885366301487239e-05, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.020888355342136854, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.020888355342136854, "padded_tokens_per_useful_token": 4.4008058364464957e-05, "padding_fraction": 6.885366301487239e-05 } }, "P09-C00-moderate": { "blocks": [ { "bucket": 4842.0, "duration_ms": 9958.405207000005, "eligible_miss": 0.0, "miss": 13.0, "model": 208.0, "overflow": 13.0, "padding": 352.0, "tokens": 50247.0 }, { "bucket": 6232.0, "duration_ms": 10019.690176, "eligible_miss": 0.0, "miss": 9.0, "model": 379.0, "overflow": 9.0, "padding": 398.0, "tokens": 34279.0 }, { "bucket": 6130.0, "duration_ms": 10012.610543, "eligible_miss": 0.0, "miss": 9.0, "model": 347.0, "overflow": 9.0, "padding": 569.0, "tokens": 38180.0 }, { "bucket": 4522.0, "duration_ms": 10068.259875999993, "eligible_miss": 0.0, "miss": 13.0, "model": 218.0, "overflow": 13.0, "padding": 309.0, "tokens": 51545.0 }, { "bucket": 4488.0, "duration_ms": 9882.649579000003, "eligible_miss": 0.0, "miss": 14.0, "model": 278.0, "overflow": 14.0, "padding": 449.0, "tokens": 44110.0 }, { "bucket": 6070.0, "duration_ms": 9947.566525999999, "eligible_miss": 0.0, "miss": 10.0, "model": 398.0, "overflow": 10.0, "padding": 462.0, "tokens": 30960.0 }, { "bucket": 5762.0, "duration_ms": 10407.604067000006, "eligible_miss": 0.0, "miss": 11.0, "model": 389.0, "overflow": 11.0, "padding": 413.0, "tokens": 39848.0 }, { "bucket": 5364.0, "duration_ms": 9508.797856999996, "eligible_miss": 0.0, "miss": 12.0, "model": 286.0, "overflow": 12.0, "padding": 461.0, "tokens": 36418.0 }, { "bucket": 4626.0, "duration_ms": 9989.894830999996, "eligible_miss": 0.0, "miss": 11.0, "model": 207.0, "overflow": 11.0, "padding": 542.0, "tokens": 50432.0 }, { "bucket": 6263.0, "duration_ms": 9985.924533000003, "eligible_miss": 0.0, "miss": 9.0, "model": 383.0, "overflow": 9.0, "padding": 479.0, "tokens": 34787.0 }, { "bucket": 4496.0, "duration_ms": 10077.274496999995, "eligible_miss": 0.0, "miss": 13.0, "model": 295.0, "overflow": 13.0, "padding": 663.0, "tokens": 44594.0 }, { "bucket": 4492.0, "duration_ms": 9866.059131999997, "eligible_miss": 0.0, "miss": 13.0, "model": 353.0, "overflow": 13.0, "padding": 445.0, "tokens": 34497.0 }, { "bucket": 4804.0, "duration_ms": 10142.781146999996, "eligible_miss": 0.0, "miss": 13.0, "model": 434.0, "overflow": 13.0, "padding": 450.0, "tokens": 31998.0 }, { "bucket": 3332.0, "duration_ms": 9844.485115999998, "eligible_miss": 0.0, "miss": 13.0, "model": 203.0, "overflow": 13.0, "padding": 238.0, "tokens": 51123.0 }, { "bucket": 6188.0, "duration_ms": 10027.362657999993, "eligible_miss": 0.0, "miss": 13.0, "model": 225.0, "overflow": 13.0, "padding": 699.0, "tokens": 44635.0 }, { "bucket": 4724.0, "duration_ms": 9965.154617999997, "eligible_miss": 0.0, "miss": 14.0, "model": 173.0, "overflow": 14.0, "padding": 434.0, "tokens": 51340.0 }, { "bucket": 5552.0, "duration_ms": 9927.860614999998, "eligible_miss": 0.0, "miss": 10.0, "model": 312.0, "overflow": 10.0, "padding": 558.0, "tokens": 37401.0 }, { "bucket": 2860.0, "duration_ms": 10211.194994999996, "eligible_miss": 0.0, "miss": 14.0, "model": 192.0, "overflow": 14.0, "padding": 182.0, "tokens": 59914.0 }, { "bucket": 5386.0, "duration_ms": 9765.457841999998, "eligible_miss": 0.0, "miss": 11.0, "model": 265.0, "overflow": 11.0, "padding": 453.0, "tokens": 40425.0 }, { "bucket": 4166.0, "duration_ms": 10272.187767999998, "eligible_miss": 0.0, "miss": 11.0, "model": 385.0, "overflow": 11.0, "padding": 242.0, "tokens": 44978.0 }, { "bucket": 5616.0, "duration_ms": 9760.582664000001, "eligible_miss": 0.0, "miss": 13.0, "model": 225.0, "overflow": 13.0, "padding": 551.0, "tokens": 45331.0 }, { "bucket": 6718.0, "duration_ms": 9900.015582000007, "eligible_miss": 0.0, "miss": 10.0, "model": 388.0, "overflow": 10.0, "padding": 359.0, "tokens": 34828.0 }, { "bucket": 4962.0, "duration_ms": 10067.267675999994, "eligible_miss": 0.0, "miss": 15.0, "model": 272.0, "overflow": 15.0, "padding": 370.0, "tokens": 48400.0 }, { "bucket": 4784.0, "duration_ms": 9941.889420000003, "eligible_miss": 0.0, "miss": 14.0, "model": 151.0, "overflow": 14.0, "padding": 566.0, "tokens": 52131.0 }, { "bucket": 4152.0, "duration_ms": 9947.915998000008, "eligible_miss": 0.0, "miss": 14.0, "model": 222.0, "overflow": 14.0, "padding": 414.0, "tokens": 49116.0 }, { "bucket": 5470.0, "duration_ms": 9983.611937999998, "eligible_miss": 0.0, "miss": 14.0, "model": 364.0, "overflow": 14.0, "padding": 547.0, "tokens": 34668.0 }, { "bucket": 3540.0, "duration_ms": 11197.859721, "eligible_miss": 0.0, "miss": 16.0, "model": 221.0, "overflow": 16.0, "padding": 221.0, "tokens": 66725.0 }, { "bucket": 6640.0, "duration_ms": 9417.335203000006, "eligible_miss": 0.0, "miss": 9.0, "model": 272.0, "overflow": 9.0, "padding": 578.0, "tokens": 32531.0 }, { "bucket": 5842.0, "duration_ms": 9879.985574999997, "eligible_miss": 0.0, "miss": 9.0, "model": 329.0, "overflow": 9.0, "padding": 450.0, "tokens": 40048.0 }, { "bucket": 2872.0, "duration_ms": 9451.456130999999, "eligible_miss": 0.0, "miss": 14.0, "model": 80.0, "overflow": 14.0, "padding": 146.0, "tokens": 61227.0 }, { "bucket": 5776.0, "duration_ms": 9994.594990999996, "eligible_miss": 0.0, "miss": 10.0, "model": 136.0, "overflow": 10.0, "padding": 378.0, "tokens": 55901.0 }, { "bucket": 5339.0, "duration_ms": 10200.117377999997, "eligible_miss": 0.0, "miss": 10.0, "model": 422.0, "overflow": 10.0, "padding": 289.0, "tokens": 38209.0 }, { "bucket": 2976.0, "duration_ms": 10224.24287, "eligible_miss": 0.0, "miss": 16.0, "model": 82.0, "overflow": 16.0, "padding": 225.0, "tokens": 64384.0 }, { "bucket": 4264.0, "duration_ms": 9567.238165000006, "eligible_miss": 0.0, "miss": 14.0, "model": 152.0, "overflow": 14.0, "padding": 401.0, "tokens": 52662.0 }, { "bucket": 5566.0, "duration_ms": 9932.33232, "eligible_miss": 0.0, "miss": 11.0, "model": 341.0, "overflow": 11.0, "padding": 537.0, "tokens": 37176.0 }, { "bucket": 6158.0, "duration_ms": 10517.70363300001, "eligible_miss": 0.0, "miss": 10.0, "model": 423.0, "overflow": 10.0, "padding": 355.0, "tokens": 36732.0 }, { "bucket": 4512.0, "duration_ms": 9502.686013999999, "eligible_miss": 0.0, "miss": 12.0, "model": 253.0, "overflow": 12.0, "padding": 379.0, "tokens": 45470.0 }, { "bucket": 4606.0, "duration_ms": 10520.496230000002, "eligible_miss": 0.0, "miss": 14.0, "model": 226.0, "overflow": 14.0, "padding": 506.0, "tokens": 55036.0 }, { "bucket": 3856.0, "duration_ms": 10017.898350999998, "eligible_miss": 0.0, "miss": 15.0, "model": 99.0, "overflow": 15.0, "padding": 311.0, "tokens": 62102.0 }, { "bucket": 4112.0, "duration_ms": 9365.698862000003, "eligible_miss": 0.0, "miss": 11.0, "model": 105.0, "overflow": 11.0, "padding": 388.0, "tokens": 52921.0 }, { "bucket": 5820.0, "duration_ms": 10483.163068999998, "eligible_miss": 0.0, "miss": 11.0, "model": 219.0, "overflow": 11.0, "padding": 689.0, "tokens": 52494.0 }, { "bucket": 5088.0, "duration_ms": 9710.597793999992, "eligible_miss": 0.0, "miss": 11.0, "model": 127.0, "overflow": 11.0, "padding": 361.0, "tokens": 51839.0 }, { "bucket": 5676.0, "duration_ms": 9812.009743999994, "eligible_miss": 0.0, "miss": 9.0, "model": 390.0, "overflow": 9.0, "padding": 382.0, "tokens": 33697.0 }, { "bucket": 5322.0, "duration_ms": 10481.612746, "eligible_miss": 0.0, "miss": 12.0, "model": 271.0, "overflow": 12.0, "padding": 493.0, "tokens": 50862.0 }, { "bucket": 5042.0, "duration_ms": 9438.804079000005, "eligible_miss": 0.0, "miss": 11.0, "model": 363.0, "overflow": 11.0, "padding": 542.0, "tokens": 32980.0 }, { "bucket": 4616.0, "duration_ms": 9963.877349000002, "eligible_miss": 0.0, "miss": 13.0, "model": 420.0, "overflow": 13.0, "padding": 285.0, "tokens": 33032.0 }, { "bucket": 4592.0, "duration_ms": 10306.957352000003, "eligible_miss": 0.0, "miss": 13.0, "model": 260.0, "overflow": 13.0, "padding": 466.0, "tokens": 49197.0 }, { "bucket": 3688.0, "duration_ms": 9934.53882, "eligible_miss": 0.0, "miss": 13.0, "model": 94.0, "overflow": 13.0, "padding": 335.0, "tokens": 61669.0 } ], "clean": { "admitted": 1181, "completed": 1185, "completed_throughput_rps": 4.9375, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 2116361, "offered_rps": 4.920833333333333, "output_tokens": 75840, "start_s": 60.0 }, "config": "C00", "drain_quarantined": false, "drain_seconds": 0.6209534369991161, "latency_s": { "e2e": { "mean": 1.6859668752037082, "n": 1185, "p50": 1.3681276970019098, "p95": 3.9139900154143104, "p99": 4.631161756748335 }, "tpot": { "mean": 0.023014267673890598, "n": 1185, "p50": 0.017877640635041252, "p95": 0.05483829206029425, "p99": 0.06860999865810366 }, "ttft": { "mean": 0.23606801174860054, "n": 1185, "p50": 0.12713102900306694, "p95": 0.7102715160115618, "p99": 1.0138114924693946 } }, "layer1": { "decode_tokens": 74436, "kv_usage_max": 0.23887537172208706, "kv_usage_mean": 0.03684185997310298, "mode_counts": { "FULL": 11783, "NONE": 580, "PIECEWISE": 474 }, "mode_shares": { "FULL": 0.9178935888447457, "NONE": 0.045181896081639014, "PIECEWISE": 0.036924515073615334 }, "preemptions": 0, "prefill_tokens": 2108643, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 1, "queue_waiting_mean": 7.789982083041208e-05, "records_all": 19341, "records_clean": 12837, "requests_per_step": { "mean": 5.891485549583236, "n": 12837, "p50": 4.0, "p95": 16.0, "p99": 21.0 }, "scheduled_tokens_per_step": { "mean": 170.0614629586352, "n": 12837, "p50": 4.0, "p95": 456.0, "p99": 5951.919999999998 }, "step_duration_ms": { "mean": 37.34546321243281, "n": 12837, "p50": 17.244659, "p95": 108.07043219999986, "p99": 478.49575835999946 }, "token_efficiency_per_ms": 4.553738214231586 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P09", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 4.949999999999999, "clean_c_waiting_median": 0.0, "completion_rate_rps": 5.3, "completion_rate_within_10pct": true, "tail_end_s": 334.5889142579981, "tail_start_s": 324.5889142579981, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 4.949999999999999, "clean_c_waiting_median": 0.0, "completion_rate_rps": 4.8, "completion_rate_within_10pct": true, "tail_end_s": 366.81370019100723, "tail_start_s": 356.81370019100723, "valid": true, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": true, "requests_completed": 1185, "run_dir": "runs/phase3/primary/P09-C00/moderate", "run_id": "P09-C00-moderate", "trace_files": 2, "waste": { "R128": 0.7696283944181126, "R32": 0.7555897047229047, "R64": 0.7648466836330938, "bucket_slack": 0.08542101015535679, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.045181896081639014, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 1054, "moe_layer_cv": null, "overflow_rate": 0.045181896081639014, "padded_tokens_per_useful_token": 0.009308870636381002, "padding_fraction": 0.08542101015535679 } }, "P09-C00-saturation": { "blocks": [ { "duration_ms": 9749.202351999998, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81920.0 }, { "duration_ms": 10176.620378000001, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81920.0 }, { "duration_ms": 9362.997435, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "bucket": 4936.0, "duration_ms": 10439.874369999998, "eligible_miss": 0.0, "miss": 9.0, "model": 37.0, "overflow": 9.0, "padding": 129.0, "tokens": 66116.0 }, { "duration_ms": 9925.238021000001, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 82014.0 }, { "duration_ms": 9704.610116999998, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81920.0 }, { "bucket": 160.0, "duration_ms": 9388.846731, "eligible_miss": 0.0, "miss": 9.0, "model": 10.0, "overflow": 9.0, "padding": 7.0, "tokens": 73377.0 }, { "bucket": 4152.0, "duration_ms": 10519.513901, "eligible_miss": 0.0, "miss": 11.0, "model": 37.0, "overflow": 11.0, "padding": 175.0, "tokens": 71992.0 }, { "duration_ms": 10267.690021, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 88360.0 }, { "duration_ms": 9614.783594, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 76869.0 }, { "bucket": 2400.0, "duration_ms": 9588.755232000001, "eligible_miss": 0.0, "miss": 8.0, "model": 23.0, "overflow": 8.0, "padding": 30.0, "tokens": 62556.0 }, { "bucket": 1912.0, "duration_ms": 10646.490665, "eligible_miss": 0.0, "miss": 11.0, "model": 23.0, "overflow": 11.0, "padding": 33.0, "tokens": 80491.0 }, { "duration_ms": 10009.880642, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 78425.0 }, { "duration_ms": 10656.483834999999, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 89372.0 }, { "bucket": 4144.0, "duration_ms": 9085.264818000003, "eligible_miss": 0.0, "miss": 7.0, "model": 33.0, "overflow": 7.0, "padding": 151.0, "tokens": 56724.0 }, { "bucket": 312.0, "duration_ms": 10100.92011, "eligible_miss": 0.0, "miss": 11.0, "model": 13.0, "overflow": 11.0, "padding": 5.0, "tokens": 84841.0 }, { "duration_ms": 10627.625256, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 84284.0 }, { "duration_ms": 10260.804656999999, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81920.0 }, { "bucket": 3264.0, "duration_ms": 9273.320073000003, "eligible_miss": 0.0, "miss": 9.0, "model": 33.0, "overflow": 9.0, "padding": 63.0, "tokens": 54343.0 }, { "bucket": 144.0, "duration_ms": 10147.99783, "eligible_miss": 0.0, "miss": 12.0, "model": 13.0, "overflow": 12.0, "padding": 4.0, "tokens": 85321.0 }, { "duration_ms": 10021.874463, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 86244.0 }, { "duration_ms": 9849.016171000001, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 78795.0 }, { "bucket": 4216.0, "duration_ms": 9761.302597000004, "eligible_miss": 0.0, "miss": 10.0, "model": 34.0, "overflow": 10.0, "padding": 44.0, "tokens": 64574.0 }, { "bucket": 304.0, "duration_ms": 10243.365921, "eligible_miss": 0.0, "miss": 11.0, "model": 13.0, "overflow": 11.0, "padding": 5.0, "tokens": 84741.0 }, { "duration_ms": 9702.099989999999, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 78863.0 }, { "duration_ms": 10873.143569999998, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 90112.0 }, { "bucket": 4192.0, "duration_ms": 9480.605753999998, "eligible_miss": 0.0, "miss": 10.0, "model": 35.0, "overflow": 10.0, "padding": 44.0, "tokens": 60971.0 }, { "bucket": 152.0, "duration_ms": 10362.664876, "eligible_miss": 0.0, "miss": 11.0, "model": 12.0, "overflow": 11.0, "padding": 5.0, "tokens": 86984.0 }, { "duration_ms": 10277.260139000002, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 86407.0 }, { "bucket": 160.0, "duration_ms": 9326.807399, "eligible_miss": 0.0, "miss": 9.0, "model": 10.0, "overflow": 9.0, "padding": 2.0, "tokens": 72897.0 }, { "bucket": 3960.0, "duration_ms": 9700.36302, "eligible_miss": 0.0, "miss": 12.0, "model": 35.0, "overflow": 12.0, "padding": 71.0, "tokens": 66285.0 }, { "duration_ms": 10365.53776, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 83470.0 }, { "duration_ms": 9817.621681, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 80495.0 }, { "bucket": 960.0, "duration_ms": 10456.115671000001, "eligible_miss": 0.0, "miss": 11.0, "model": 17.0, "overflow": 11.0, "padding": 14.0, "tokens": 79230.0 }, { "bucket": 3184.0, "duration_ms": 9856.080246000001, "eligible_miss": 0.0, "miss": 11.0, "model": 30.0, "overflow": 11.0, "padding": 104.0, "tokens": 71349.0 }, { "duration_ms": 9921.03899, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 78306.0 }, { "duration_ms": 10466.651198, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81920.0 }, { "bucket": 856.0, "duration_ms": 8754.815939, "eligible_miss": 0.0, "miss": 9.0, "model": 15.0, "overflow": 9.0, "padding": 33.0, "tokens": 63314.0 }, { "bucket": 2688.0, "duration_ms": 11187.383653000003, "eligible_miss": 0.0, "miss": 12.0, "model": 32.0, "overflow": 12.0, "padding": 59.0, "tokens": 82299.0 }, { "duration_ms": 9584.902875, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 79102.0 }, { "duration_ms": 10227.432321, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 81437.0 }, { "bucket": 3528.0, "duration_ms": 8850.584567999998, "eligible_miss": 0.0, "miss": 8.0, "model": 29.0, "overflow": 8.0, "padding": 100.0, "tokens": 59108.0 }, { "bucket": 488.0, "duration_ms": 10674.824159000002, "eligible_miss": 0.0, "miss": 14.0, "model": 17.0, "overflow": 14.0, "padding": 18.0, "tokens": 82423.0 }, { "duration_ms": 10659.708045999998, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 89002.0 }, { "duration_ms": 9632.058042, "eligible_miss": 0.0, "miss": 10.0, "model": 10.0, "overflow": 10.0, "tokens": 76260.0 }, { "bucket": 3168.0, "duration_ms": 9123.113560000002, "eligible_miss": 0.0, "miss": 7.0, "model": 29.0, "overflow": 7.0, "padding": 90.0, "tokens": 52910.0 }, { "bucket": 456.0, "duration_ms": 10462.624554999999, "eligible_miss": 0.0, "miss": 14.0, "model": 17.0, "overflow": 14.0, "padding": 6.0, "tokens": 89979.0 }, { "duration_ms": 10867.76237, "eligible_miss": 0.0, "miss": 11.0, "model": 11.0, "overflow": 11.0, "tokens": 88279.0 } ], "clean": { "admitted": 1969, "completed": 1969, "completed_throughput_rps": 8.204166666666667, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 3580022, "offered_rps": 8.204166666666667, "output_tokens": 126016, "start_s": 60.0 }, "config": "C00", "drain_quarantined": false, "drain_seconds": 16.845643790991744, "latency_s": { "e2e": { "mean": 31.15778886316919, "n": 1969, "p50": 31.64944553602254, "p95": 34.37905165641568, "p99": 35.391083135553636 }, "tpot": { "mean": 0.28642918251555166, "n": 1969, "p50": 0.28561478876231594, "p95": 0.29734348012356177, "p99": 0.30687090564979286 }, "ttft": { "mean": 13.112750364689438, "n": 1969, "p50": 13.525480992015218, "p95": 16.44797444838332, "p99": 17.28292753903661 } }, "layer1": { "decode_tokens": 130074, "kv_usage_max": 0.9999459313327926, "kv_usage_mean": 0.9840891207267473, "mode_counts": { "FULL": 309, "NONE": 495, "PIECEWISE": 2 }, "mode_shares": { "FULL": 0.38337468982630274, "NONE": 0.6141439205955335, "PIECEWISE": 0.0024813895781637717 }, "preemptions": 14, "prefill_tokens": 3582175, "prefix_query_hit_ratio": 0.0, "queue_waiting_max": 130, "queue_waiting_mean": 98.75930521091811, "records_all": 1390, "records_clean": 806, "requests_per_step": { "mean": 152.36352357320098, "n": 806, "p50": 153.0, "p95": 170.0, "p99": 176.0 }, "scheduled_tokens_per_step": { "mean": 4605.7679900744415, "n": 806, "p50": 7108.5, "p95": 8192.0, "p99": 8192.0 }, "step_duration_ms": { "mean": 595.6000987245658, "n": 806, "p50": 742.1835209999999, "p95": 1068.00519675, "p99": 1104.1620354000001 }, "token_efficiency_per_ms": 7.732987284483932 }, "layer2_missing_after_controller_cleanup": false, "load": "saturation", "pattern": "P09", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 7.85, "clean_c_waiting_median": 98.0, "completion_rate_rps": 9.1, "completion_rate_within_10pct": false, "tail_end_s": 358.2478721680236, "tail_start_s": 348.2478721680236, "valid": false, "waiting_median": 90.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 7.85, "clean_c_waiting_median": 98.0, "completion_rate_rps": 8.0, "completion_rate_within_10pct": true, "tail_end_s": 417.95203437501914, "tail_start_s": 407.95203437501914, "valid": false, "waiting_median": 88.0, "waiting_within_10pct": false, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 1969, "run_dir": "runs/phase3/primary/P09-C00/saturation", "run_id": "P09-C00-saturation", "trace_files": 2, "waste": { "R128": 0.7696283944181126, "R32": 0.7555897047229047, "R64": 0.7648466836330938, "bucket_slack": 0.023966543348882097, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.6141439205955335, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.6141439205955335, "padded_tokens_per_useful_token": 0.000321099150407206, "padding_fraction": 0.023966543348882097 } }, "P10-C00-moderate": { "blocks": [ { "bucket": 617.0, "duration_ms": 8382.640889000002, "eligible_miss": 0.0, "miss": 3.0, "model": 620.0, "overflow": 3.0, "padding": 0.0, "tokens": 14884.0 }, { "bucket": 126.0, "duration_ms": 11045.799707, "eligible_miss": 0.0, "miss": 6.0, "model": 128.0, "overflow": 6.0, "padding": 1.0, "tokens": 44858.0 }, { "bucket": 152.0, "duration_ms": 8970.843604999998, "eligible_miss": 0.0, "miss": 6.0, "model": 27.0, "overflow": 6.0, "padding": 51.0, "tokens": 42577.0 }, { "bucket": 1504.0, "duration_ms": 10324.448034000003, "eligible_miss": 0.0, "miss": 4.0, "model": 192.0, "overflow": 4.0, "padding": 488.0, "tokens": 24681.0 }, { "bucket": 770.0, "duration_ms": 11102.520114999996, "eligible_miss": 0.0, "miss": 6.0, "model": 231.0, "overflow": 6.0, "padding": 111.0, "tokens": 43629.0 }, { "bucket": 1160.0, "duration_ms": 8529.057380000006, "eligible_miss": 0.0, "miss": 3.0, "model": 166.0, "overflow": 3.0, "padding": 117.0, "tokens": 15737.0 }, { "bucket": 688.0, "duration_ms": 5848.787868000003, "eligible_miss": 0.0, "miss": 2.0, "model": 476.0, "overflow": 2.0, "padding": 46.0, "tokens": 4992.0 }, { "bucket": 255.0, "duration_ms": 9870.306260000001, "eligible_miss": 0.0, "miss": 5.0, "model": 260.0, "overflow": 5.0, "padding": 0.0, "tokens": 35214.0 }, { "bucket": 272.0, "duration_ms": 7990.321079999999, "eligible_miss": 0.0, "miss": 4.0, "model": 72.0, "overflow": 4.0, "padding": 7.0, "tokens": 28400.0 }, { "bucket": 1302.0, "duration_ms": 9966.716543000008, "eligible_miss": 0.0, "miss": 4.0, "model": 237.0, "overflow": 4.0, "padding": 243.0, "tokens": 23279.0 }, { "bucket": 448.0, "duration_ms": 11609.913073999996, "eligible_miss": 0.0, "miss": 6.0, "model": 132.0, "overflow": 6.0, "padding": 9.0, "tokens": 43441.0 }, { "bucket": 1565.0, "duration_ms": 8345.582649000005, "eligible_miss": 0.0, "miss": 2.0, "model": 496.0, "overflow": 2.0, "padding": 83.0, "tokens": 12026.0 }, { "bucket": 211.0, "duration_ms": 5952.138712999998, "eligible_miss": 0.0, "miss": 5.0, "model": 215.0, "overflow": 5.0, "padding": 0.0, "tokens": 21433.0 }, { "bucket": 488.0, "duration_ms": 8490.797738000003, "eligible_miss": 0.0, "miss": 4.0, "model": 354.0, "overflow": 4.0, "padding": 0.0, "tokens": 25206.0 }, { "bucket": 610.0, "duration_ms": 6998.942739000001, "eligible_miss": 0.0, "miss": 3.0, "model": 489.0, "overflow": 3.0, "padding": 0.0, "tokens": 14062.0 }, { "bucket": 423.0, "duration_ms": 8712.311025000003, "eligible_miss": 0.0, "miss": 5.0, "model": 428.0, "overflow": 5.0, "padding": 0.0, "tokens": 33204.0 }, { "bucket": 822.0, "duration_ms": 7311.043669000002, "eligible_miss": 0.0, "miss": 2.0, "model": 465.0, "overflow": 2.0, "padding": 3.0, "tokens": 9758.0 }, { "bucket": 699.0, "duration_ms": 3225.8468359999983, "eligible_miss": 0.0, "miss": 1.0, "model": 333.0, "overflow": 1.0, "padding": 1.0, "tokens": 1714.0 }, { "bucket": 990.0, "duration_ms": 9264.891035000004, "eligible_miss": 0.0, "miss": 4.0, "model": 445.0, "overflow": 4.0, "padding": 4.0, "tokens": 28155.0 }, { "bucket": 466.0, "duration_ms": 9110.875763999999, "eligible_miss": 0.0, "miss": 4.0, "model": 401.0, "overflow": 4.0, "padding": 0.0, "tokens": 31929.0 }, { "bucket": 1071.0, "duration_ms": 6715.519883000001, "eligible_miss": 0.0, "miss": 2.0, "model": 382.0, "overflow": 2.0, "padding": 18.0, "tokens": 7012.0 }, { "bucket": 550.0, "duration_ms": 3031.6539789999974, "eligible_miss": 0.0, "miss": 1.0, "model": 329.0, "overflow": 1.0, "padding": 8.0, "tokens": 1755.0 }, { "bucket": 376.0, "duration_ms": 5516.428338, "eligible_miss": 0.0, "miss": 3.0, "model": 379.0, "overflow": 3.0, "padding": 0.0, "tokens": 14766.0 }, { "bucket": 1075.0, "duration_ms": 7219.809630999999, "eligible_miss": 0.0, "miss": 3.0, "model": 480.0, "overflow": 3.0, "padding": 13.0, "tokens": 19060.0 }, { "bucket": 337.0, "duration_ms": 9648.578009, "eligible_miss": 0.0, "miss": 5.0, "model": 341.0, "overflow": 5.0, "padding": 0.0, "tokens": 34101.0 }, { "bucket": 946.0, "duration_ms": 8697.491265, "eligible_miss": 0.0, "miss": 3.0, "model": 480.0, "overflow": 3.0, "padding": 86.0, "tokens": 17701.0 }, { "bucket": 554.0, "duration_ms": 9683.282806000003, "eligible_miss": 0.0, "miss": 5.0, "model": 559.0, "overflow": 5.0, "padding": 0.0, "tokens": 32266.0 }, { "bucket": 678.0, "duration_ms": 7048.451871000006, "eligible_miss": 0.0, "miss": 1.0, "model": 545.0, "overflow": 1.0, "padding": 3.0, "tokens": 7876.0 }, { "bucket": 646.0, "duration_ms": 8348.867864999998, "eligible_miss": 0.0, "miss": 3.0, "model": 649.0, "overflow": 3.0, "padding": 0.0, "tokens": 15839.0 }, { "bucket": 256.0, "duration_ms": 7786.6034809999965, "eligible_miss": 0.0, "miss": 4.0, "model": 260.0, "overflow": 4.0, "padding": 0.0, "tokens": 25371.0 }, { "bucket": 740.0, "duration_ms": 9608.457868999996, "eligible_miss": 0.0, "miss": 6.0, "model": 191.0, "overflow": 6.0, "padding": 182.0, "tokens": 33852.0 }, { "bucket": 1045.0, "duration_ms": 9948.261445000006, "eligible_miss": 0.0, "miss": 4.0, "model": 399.0, "overflow": 4.0, "padding": 101.0, "tokens": 21987.0 }, { "bucket": 499.0, "duration_ms": 5516.342829999998, "eligible_miss": 0.0, "miss": 3.0, "model": 502.0, "overflow": 3.0, "padding": 0.0, "tokens": 10171.0 }, { "bucket": 414.0, "duration_ms": 8107.245063000002, "eligible_miss": 0.0, "miss": 4.0, "model": 418.0, "overflow": 4.0, "padding": 0.0, "tokens": 26442.0 }, { "bucket": 920.0, "duration_ms": 7048.238840000001, "eligible_miss": 0.0, "miss": 1.0, "model": 501.0, "overflow": 1.0, "padding": 1.0, "tokens": 4144.0 }, { "bucket": 335.0, "duration_ms": 5664.3669340000015, "eligible_miss": 0.0, "miss": 3.0, "model": 338.0, "overflow": 3.0, "padding": 0.0, "tokens": 16438.0 }, { "bucket": 984.0, "duration_ms": 8897.687465000003, "eligible_miss": 0.0, "miss": 4.0, "model": 340.0, "overflow": 4.0, "padding": 34.0, "tokens": 26851.0 }, { "bucket": 951.0, "duration_ms": 5888.0405209999935, "eligible_miss": 0.0, "miss": 1.0, "model": 494.0, "overflow": 1.0, "padding": 13.0, "tokens": 7545.0 }, { "bucket": 635.0, "duration_ms": 6843.962990000004, "eligible_miss": 0.0, "miss": 2.0, "model": 637.0, "overflow": 2.0, "padding": 0.0, "tokens": 10109.0 }, { "bucket": 326.0, "duration_ms": 10501.115293, "eligible_miss": 0.0, "miss": 6.0, "model": 332.0, "overflow": 6.0, "padding": 0.0, "tokens": 36220.0 }, { "bucket": 935.0, "duration_ms": 6618.986783999992, "eligible_miss": 0.0, "miss": 3.0, "model": 494.0, "overflow": 3.0, "padding": 95.0, "tokens": 3782.0 }, { "bucket": 512.0, "duration_ms": 8131.997052, "eligible_miss": 0.0, "miss": 4.0, "model": 490.0, "overflow": 4.0, "padding": 0.0, "tokens": 22549.0 }, { "bucket": 742.0, "duration_ms": 9767.929607000004, "eligible_miss": 0.0, "miss": 3.0, "model": 414.0, "overflow": 3.0, "padding": 5.0, "tokens": 23222.0 }, { "bucket": 639.0, "duration_ms": 5619.278247999995, "eligible_miss": 0.0, "miss": 2.0, "model": 609.0, "overflow": 2.0, "padding": 4.0, "tokens": 2804.0 }, { "bucket": 887.0, "duration_ms": 3543.163819999999, "eligible_miss": 0.0, "miss": 1.0, "model": 250.0, "overflow": 1.0, "padding": 3.0, "tokens": 9076.0 }, { "bucket": 576.0, "duration_ms": 8349.781138999993, "eligible_miss": 0.0, "miss": 4.0, "model": 580.0, "overflow": 4.0, "padding": 0.0, "tokens": 21628.0 }, { "bucket": 457.0, "duration_ms": 11131.830392999998, "eligible_miss": 0.0, "miss": 5.0, "model": 432.0, "overflow": 5.0, "padding": 0.0, "tokens": 39509.0 }, { "bucket": 564.0, "duration_ms": 7224.973540000003, "eligible_miss": 0.0, "miss": 2.0, "model": 138.0, "overflow": 2.0, "padding": 63.0, "tokens": 12290.0 } ], "clean": { "admitted": 113, "completed": 111, "completed_throughput_rps": 0.4625, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 968714, "offered_rps": 0.4708333333333333, "output_tokens": 25409, "start_s": 60.0 }, "config": "C00", "drain_quarantined": false, "drain_seconds": 1.3658369119802956, "latency_s": { "e2e": { "mean": 3.3829411591981593, "n": 111, "p50": 2.0798101979889907, "p95": 10.049355082010152, "p99": 13.440132959096816 }, "tpot": { "mean": 0.010226489478255945, "n": 111, "p50": 0.0059010086391650726, "p95": 0.029376378439209316, "p99": 0.04181571422473475 }, "ttft": { "mean": 0.9392844953882059, "n": 111, "p50": 0.6116193659836426, "p95": 3.0904414410033496, "p99": 4.187785376003013 } }, "layer1": { "decode_tokens": 25704, "kv_usage_max": 0.38664503919978377, "kv_usage_mean": 0.04570683788470549, "mode_counts": { "FULL": 17941, "NONE": 283, "PIECEWISE": 22 }, "mode_shares": { "FULL": 0.9832840074536885, "NONE": 0.015510248821659542, "PIECEWISE": 0.0012057437246519786 }, "preemptions": 0, "prefill_tokens": 977841, "prefix_query_hit_ratio": 0.017412117941776724, "queue_waiting_max": 1, "queue_waiting_mean": 5.4806532938726295e-05, "records_all": 26343, "records_clean": 18246, "requests_per_step": { "mean": 1.4192151704483174, "n": 18246, "p50": 1.0, "p95": 4.0, "p99": 6.0 }, "scheduled_tokens_per_step": { "mean": 55.00082209799408, "n": 18246, "p50": 1.0, "p95": 4.0, "p99": 59.29999999998108 }, "step_duration_ms": { "mean": 20.99978799101173, "n": 18246, "p50": 9.6838665, "p95": 22.50289075, "p99": 282.73305594999846 }, "token_efficiency_per_ms": 2.6191132082635966 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P10", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 0.5, "clean_c_waiting_median": 0.0, "completion_rate_rps": 0.6, "completion_rate_within_10pct": false, "tail_end_s": 331.62960390897933, "tail_start_s": 321.62960390897933, "valid": false, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 0.5, "clean_c_waiting_median": 0.0, "completion_rate_rps": 0.8, "completion_rate_within_10pct": false, "tail_end_s": 363.15318555399426, "tail_start_s": 353.15318555399426, "valid": false, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 111, "run_dir": "runs/phase3/primary/P10-C00/moderate", "run_id": "P10-C00-moderate", "trace_files": 2, "waste": { "R128": 0.7047173851989379, "R32": 0.6764453342592629, "R64": 0.6923054365307624, "bucket_slack": 0.05565211993295673, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.009211252068394925, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 92, "moe_layer_cv": null, "overflow_rate": 0.009211252068394925, "padded_tokens_per_useful_token": 0.0017866662680796576, "padding_fraction": 0.05565211993295673 } }, "P10-C00-saturation": { "blocks": [ { "bucket": 1176.0, "duration_ms": 10009.811425999998, "eligible_miss": 0.0, "miss": 4.0, "model": 53.0, "overflow": 4.0, "padding": 343.0, "tokens": 26342.0 }, { "bucket": 2128.0, "duration_ms": 9992.710429, "eligible_miss": 0.0, "miss": 3.0, "model": 92.0, "overflow": 3.0, "padding": 600.0, "tokens": 24128.0 }, { "bucket": 528.0, "duration_ms": 11089.164078, "eligible_miss": 0.0, "miss": 9.0, "model": 31.0, "overflow": 9.0, "padding": 111.0, "tokens": 67385.0 }, { "bucket": 48.0, "duration_ms": 9556.7498, "eligible_miss": 0.0, "miss": 9.0, "model": 10.0, "overflow": 9.0, "padding": 6.0, "tokens": 70830.0 }, { "duration_ms": 10951.74559, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "duration_ms": 9388.825067, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 59522.0 }, { "bucket": 6592.0, "duration_ms": 9039.374405999999, "eligible_miss": 0.0, "miss": 1.0, "model": 107.0, "overflow": 1.0, "padding": 249.0, "tokens": 8794.0 }, { "bucket": 4312.0, "duration_ms": 11316.996691999995, "eligible_miss": 0.0, "miss": 7.0, "model": 84.0, "overflow": 7.0, "padding": 188.0, "tokens": 43138.0 }, { "bucket": 1736.0, "duration_ms": 9279.988393, "eligible_miss": 0.0, "miss": 7.0, "model": 38.0, "overflow": 7.0, "padding": 99.0, "tokens": 50096.0 }, { "duration_ms": 9763.796564999999, "eligible_miss": 0.0, "miss": 8.0, "model": 8.0, "overflow": 8.0, "tokens": 61672.0 }, { "bucket": 48.0, "duration_ms": 10376.027167, "eligible_miss": 0.0, "miss": 9.0, "model": 10.0, "overflow": 9.0, "padding": 2.0, "tokens": 70629.0 }, { "duration_ms": 10483.151265999999, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 68074.0 }, { "bucket": 5544.0, "duration_ms": 8734.690442000003, "eligible_miss": 0.0, "miss": 2.0, "model": 105.0, "overflow": 2.0, "padding": 266.0, "tokens": 10348.0 }, { "bucket": 2784.0, "duration_ms": 10805.742734, "eligible_miss": 0.0, "miss": 4.0, "model": 62.0, "overflow": 4.0, "padding": 226.0, "tokens": 29614.0 }, { "bucket": 1208.0, "duration_ms": 9140.551409, "eligible_miss": 0.0, "miss": 4.0, "model": 30.0, "overflow": 4.0, "padding": 140.0, "tokens": 27875.0 }, { "bucket": 1184.0, "duration_ms": 11310.472485, "eligible_miss": 0.0, "miss": 6.0, "model": 36.0, "overflow": 6.0, "padding": 74.0, "tokens": 44653.0 }, { "duration_ms": 9714.580936, "eligible_miss": 0.0, "miss": 5.0, "model": 5.0, "overflow": 5.0, "tokens": 40960.0 }, { "bucket": 320.0, "duration_ms": 10471.643823999999, "eligible_miss": 0.0, "miss": 5.0, "model": 8.0, "overflow": 5.0, "padding": 7.0, "tokens": 41273.0 }, { "duration_ms": 10020.970553999998, "eligible_miss": 0.0, "miss": 5.0, "model": 5.0, "overflow": 5.0, "tokens": 40960.0 }, { "duration_ms": 10602.244435999999, "eligible_miss": 0.0, "miss": 6.0, "model": 6.0, "overflow": 6.0, "tokens": 49152.0 }, { "bucket": 144.0, "duration_ms": 8836.206753999999, "eligible_miss": 0.0, "miss": 5.0, "model": 14.0, "overflow": 5.0, "padding": 20.0, "tokens": 40196.0 }, { "bucket": 2032.0, "duration_ms": 9019.412542, "eligible_miss": 0.0, "miss": 0.0, "model": 127.0, "overflow": 0.0, "padding": 329.0, "tokens": 1703.0 }, { "bucket": 944.0, "duration_ms": 10821.127354, "eligible_miss": 0.0, "miss": 6.0, "model": 65.0, "overflow": 6.0, "padding": 173.0, "tokens": 44294.0 }, { "bucket": 624.0, "duration_ms": 9594.954417999998, "eligible_miss": 0.0, "miss": 5.0, "model": 25.0, "overflow": 5.0, "padding": 20.0, "tokens": 35181.0 }, { "bucket": 48.0, "duration_ms": 11813.587782999999, "eligible_miss": 0.0, "miss": 7.0, "model": 10.0, "overflow": 7.0, "padding": 3.0, "tokens": 56898.0 }, { "bucket": 80.0, "duration_ms": 9131.614881000001, "eligible_miss": 0.0, "miss": 7.0, "model": 12.0, "overflow": 7.0, "padding": 1.0, "tokens": 55677.0 }, { "duration_ms": 9896.023617, "eligible_miss": 0.0, "miss": 6.0, "model": 6.0, "overflow": 6.0, "tokens": 49152.0 }, { "bucket": 168.0, "duration_ms": 9331.333203999999, "eligible_miss": 0.0, "miss": 6.0, "model": 13.0, "overflow": 6.0, "padding": 43.0, "tokens": 46277.0 }, { "bucket": 1752.0, "duration_ms": 9416.513950000002, "eligible_miss": 0.0, "miss": 3.0, "model": 76.0, "overflow": 3.0, "padding": 439.0, "tokens": 18675.0 }, { "bucket": 1848.0, "duration_ms": 10004.734847999993, "eligible_miss": 0.0, "miss": 3.0, "model": 80.0, "overflow": 3.0, "padding": 463.0, "tokens": 21615.0 }, { "bucket": 736.0, "duration_ms": 11113.904184, "eligible_miss": 0.0, "miss": 7.0, "model": 38.0, "overflow": 7.0, "padding": 186.0, "tokens": 51247.0 }, { "bucket": 424.0, "duration_ms": 10244.33515, "eligible_miss": 0.0, "miss": 6.0, "model": 24.0, "overflow": 6.0, "padding": 119.0, "tokens": 44715.0 }, { "bucket": 144.0, "duration_ms": 10147.747402, "eligible_miss": 0.0, "miss": 5.0, "model": 9.0, "overflow": 5.0, "padding": 21.0, "tokens": 41083.0 }, { "bucket": 112.0, "duration_ms": 10365.436959, "eligible_miss": 0.0, "miss": 5.0, "model": 11.0, "overflow": 5.0, "padding": 15.0, "tokens": 40790.0 }, { "bucket": 64.0, "duration_ms": 9517.532987999999, "eligible_miss": 0.0, "miss": 5.0, "model": 9.0, "overflow": 5.0, "padding": 4.0, "tokens": 41020.0 }, { "bucket": 832.0, "duration_ms": 8581.742997, "eligible_miss": 0.0, "miss": 4.0, "model": 26.0, "overflow": 4.0, "padding": 54.0, "tokens": 26461.0 }, { "bucket": 1536.0, "duration_ms": 10026.462834999997, "eligible_miss": 0.0, "miss": 3.0, "model": 99.0, "overflow": 3.0, "padding": 221.0, "tokens": 19754.0 }, { "bucket": 128.0, "duration_ms": 10718.594011999998, "eligible_miss": 0.0, "miss": 6.0, "model": 14.0, "overflow": 6.0, "padding": 24.0, "tokens": 44891.0 }, { "bucket": 960.0, "duration_ms": 11535.182276, "eligible_miss": 0.0, "miss": 6.0, "model": 66.0, "overflow": 6.0, "padding": 166.0, "tokens": 38927.0 }, { "bucket": 752.0, "duration_ms": 7739.217905, "eligible_miss": 0.0, "miss": 3.0, "model": 23.0, "overflow": 3.0, "padding": 82.0, "tokens": 25246.0 }, { "bucket": 128.0, "duration_ms": 11694.124687000001, "eligible_miss": 0.0, "miss": 6.0, "model": 14.0, "overflow": 6.0, "padding": 33.0, "tokens": 48548.0 }, { "bucket": 144.0, "duration_ms": 8799.382035999999, "eligible_miss": 0.0, "miss": 5.0, "model": 14.0, "overflow": 5.0, "padding": 38.0, "tokens": 37550.0 }, { "duration_ms": 12679.302825, "eligible_miss": 0.0, "miss": 6.0, "model": 6.0, "overflow": 6.0, "tokens": 49152.0 }, { "bucket": 64.0, "duration_ms": 8103.778363, "eligible_miss": 0.0, "miss": 4.0, "model": 8.0, "overflow": 4.0, "padding": 17.0, "tokens": 29351.0 }, { "bucket": 1584.0, "duration_ms": 8692.517480999999, "eligible_miss": 0.0, "miss": 1.0, "model": 100.0, "overflow": 1.0, "padding": 429.0, "tokens": 2044.0 }, { "bucket": 352.0, "duration_ms": 11405.081409999999, "eligible_miss": 0.0, "miss": 6.0, "model": 28.0, "overflow": 6.0, "padding": 111.0, "tokens": 49393.0 }, { "bucket": 848.0, "duration_ms": 11003.100921, "eligible_miss": 0.0, "miss": 5.0, "model": 58.0, "overflow": 5.0, "padding": 213.0, "tokens": 31053.0 }, { "bucket": 144.0, "duration_ms": 8373.303938000001, "eligible_miss": 0.0, "miss": 6.0, "model": 15.0, "overflow": 6.0, "padding": 18.0, "tokens": 43909.0 } ], "clean": { "admitted": 189, "completed": 189, "completed_throughput_rps": 0.7875, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 1905018, "offered_rps": 0.7875, "output_tokens": 43531, "start_s": 60.0 }, "config": "C00", "drain_quarantined": false, "drain_seconds": 264.76528122398304, "latency_s": { "e2e": { "mean": 147.21125181689527, "n": 189, "p50": 127.2441149209917, "p95": 264.33665179300004, "p99": 293.5073658543558 }, "tpot": { "mean": 0.13403168434781512, "n": 189, "p50": 0.12877863171766055, "p95": 0.17072597033296066, "p99": 0.34752630997851625 }, "ttft": { "mean": 117.40516835215816, "n": 189, "p50": 105.56007634400157, "p95": 230.40205931000526, "p99": 254.36873530238168 } }, "layer1": { "decode_tokens": 49088, "kv_usage_max": 1.0, "kv_usage_mean": 0.9654548095061397, "mode_counts": { "FULL": 1444, "NONE": 258, "PIECEWISE": 5 }, "mode_shares": { "FULL": 0.8459285295840656, "NONE": 0.15114235500878734, "PIECEWISE": 0.0029291154071470417 }, "preemptions": 3, "prefill_tokens": 1894887, "prefix_query_hit_ratio": 0.00428220027136565, "queue_waiting_max": 245, "queue_waiting_mean": 230.05799648506152, "records_all": 4556, "records_clean": 1707, "requests_per_step": { "mean": 25.708845928529584, "n": 1707, "p50": 17.0, "p95": 57.0, "p99": 63.0 }, "scheduled_tokens_per_step": { "mean": 1138.825424721734, "n": 1707, "p50": 18.0, "p95": 8192.0, "p99": 8192.0 }, "step_duration_ms": { "mean": 281.5790834323375, "n": 1707, "p50": 74.93868, "p95": 1529.4904996999996, "p99": 2280.0959513600005 }, "token_efficiency_per_ms": 4.044424787664991 }, "layer2_missing_after_controller_cleanup": false, "load": "saturation", "pattern": "P10", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 0.35, "clean_c_waiting_median": 243.0, "completion_rate_rps": 0.7, "completion_rate_within_10pct": false, "tail_end_s": 332.293171702011, "tail_start_s": 322.293171702011, "valid": false, "waiting_median": 218.0, "waiting_within_10pct": false, "window": 1 }, { "clean_c_completion_rate_median_rps": 0.35, "clean_c_waiting_median": 243.0, "completion_rate_rps": 0.6, "completion_rate_within_10pct": false, "tail_end_s": 367.90418185602175, "tail_start_s": 357.90418185602175, "valid": false, "waiting_median": 233.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 189, "run_dir": "runs/phase3/primary/P10-C00/saturation", "run_id": "P10-C00-saturation", "trace_files": 2, "waste": { "R128": 0.7047173851989379, "R32": 0.6764453342592629, "R64": 0.6923054365307624, "bucket_slack": 0.12563348416289594, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.15114235500878734, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.15114235500878734, "padded_tokens_per_useful_token": 0.0028565182165408505, "padding_fraction": 0.12563348416289594 } }, "P10-C01-moderate": { "blocks": [ { "bucket": 443.0, "duration_ms": 7410.423085999997, "eligible_miss": 0.0, "miss": 10.0, "model": 453.0, "overflow": 10.0, "padding": 0.0, "tokens": 19475.0 }, { "bucket": 521.0, "duration_ms": 8271.043127999998, "eligible_miss": 0.0, "miss": 12.0, "model": 533.0, "overflow": 12.0, "padding": 0.0, "tokens": 22979.0 }, { "duration_ms": 9669.505019, "eligible_miss": 0.0, "miss": 19.0, "model": 19.0, "overflow": 19.0, "tokens": 38912.0 }, { "bucket": 148.0, "duration_ms": 9878.223238999995, "eligible_miss": 0.0, "miss": 21.0, "model": 40.0, "overflow": 21.0, "padding": 54.0, "tokens": 40191.0 }, { "bucket": 1408.0, "duration_ms": 10418.856203999998, "eligible_miss": 0.0, "miss": 12.0, "model": 188.0, "overflow": 12.0, "padding": 452.0, "tokens": 24661.0 }, { "bucket": 720.0, "duration_ms": 9851.350958, "eligible_miss": 0.0, "miss": 16.0, "model": 245.0, "overflow": 16.0, "padding": 105.0, "tokens": 31329.0 }, { "bucket": 736.0, "duration_ms": 9674.858718000003, "eligible_miss": 0.0, "miss": 14.0, "model": 127.0, "overflow": 14.0, "padding": 95.0, "tokens": 27804.0 }, { "bucket": 827.0, "duration_ms": 6290.920664999996, "eligible_miss": 0.0, "miss": 3.0, "model": 505.0, "overflow": 3.0, "padding": 46.0, "tokens": 5131.0 }, { "bucket": 715.0, "duration_ms": 6676.0982399999975, "eligible_miss": 0.0, "miss": 10.0, "model": 326.0, "overflow": 10.0, "padding": 0.0, "tokens": 21195.0 }, { "duration_ms": 10065.836480000002, "eligible_miss": 0.0, "miss": 17.0, "model": 17.0, "overflow": 17.0, "tokens": 34476.0 }, { "bucket": 784.0, "duration_ms": 9484.886980999998, "eligible_miss": 0.0, "miss": 15.0, "model": 137.0, "overflow": 15.0, "padding": 24.0, "tokens": 30505.0 }, { "bucket": 1144.0, "duration_ms": 10797.808420000001, "eligible_miss": 0.0, "miss": 13.0, "model": 166.0, "overflow": 13.0, "padding": 249.0, "tokens": 27519.0 }, { "bucket": 1316.0, "duration_ms": 9174.807360999997, "eligible_miss": 0.0, "miss": 12.0, "model": 235.0, "overflow": 12.0, "padding": 74.0, "tokens": 25760.0 }, { "bucket": 1121.0, "duration_ms": 6238.404124999998, "eligible_miss": 0.0, "miss": 2.0, "model": 547.0, "overflow": 2.0, "padding": 28.0, "tokens": 3805.0 }, { "bucket": 326.0, "duration_ms": 7573.451611000008, "eligible_miss": 0.0, "miss": 13.0, "model": 267.0, "overflow": 13.0, "padding": 0.0, "tokens": 24980.0 }, { "bucket": 986.0, "duration_ms": 10151.806548, "eligible_miss": 0.0, "miss": 16.0, "model": 331.0, "overflow": 16.0, "padding": 3.0, "tokens": 33019.0 }, { "bucket": 515.0, "duration_ms": 5298.552034000004, "eligible_miss": 0.0, "miss": 3.0, "model": 518.0, "overflow": 3.0, "padding": 0.0, "tokens": 4947.0 }, { "bucket": 345.0, "duration_ms": 8100.068032000006, "eligible_miss": 0.0, "miss": 15.0, "model": 239.0, "overflow": 15.0, "padding": 2.0, "tokens": 30160.0 }, { "bucket": 936.0, "duration_ms": 7808.381264000005, "eligible_miss": 0.0, "miss": 5.0, "model": 601.0, "overflow": 5.0, "padding": 3.0, "tokens": 9872.0 }, { "bucket": 544.0, "duration_ms": 2734.374267999999, "eligible_miss": 0.0, "miss": 5.0, "model": 182.0, "overflow": 5.0, "padding": 1.0, "tokens": 9751.0 }, { "bucket": 1125.0, "duration_ms": 9574.814693000002, "eligible_miss": 0.0, "miss": 10.0, "model": 516.0, "overflow": 10.0, "padding": 4.0, "tokens": 20098.0 }, { "bucket": 331.0, "duration_ms": 7593.752275999999, "eligible_miss": 0.0, "miss": 13.0, "model": 340.0, "overflow": 13.0, "padding": 0.0, "tokens": 25650.0 }, { "bucket": 1070.0, "duration_ms": 7976.790719999997, "eligible_miss": 0.0, "miss": 6.0, "model": 385.0, "overflow": 6.0, "padding": 18.0, "tokens": 13156.0 }, { "bucket": 503.0, "duration_ms": 2601.4658710000012, "eligible_miss": 0.0, "miss": 1.0, "model": 282.0, "overflow": 1.0, "padding": 8.0, "tokens": 1708.0 }, { "bucket": 302.0, "duration_ms": 4862.400702999999, "eligible_miss": 0.0, "miss": 8.0, "model": 310.0, "overflow": 8.0, "padding": 0.0, "tokens": 14692.0 }, { "bucket": 844.0, "duration_ms": 7449.2967190000045, "eligible_miss": 0.0, "miss": 5.0, "model": 602.0, "overflow": 5.0, "padding": 0.0, "tokens": 10650.0 }, { "bucket": 608.0, "duration_ms": 7460.192439999997, "eligible_miss": 0.0, "miss": 13.0, "model": 270.0, "overflow": 13.0, "padding": 13.0, "tokens": 26433.0 }, { "bucket": 794.0, "duration_ms": 9665.416551, "eligible_miss": 0.0, "miss": 12.0, "model": 383.0, "overflow": 12.0, "padding": 86.0, "tokens": 24648.0 }, { "bucket": 545.0, "duration_ms": 8619.111659999997, "eligible_miss": 0.0, "miss": 13.0, "model": 527.0, "overflow": 13.0, "padding": 0.0, "tokens": 25532.0 }, { "bucket": 719.0, "duration_ms": 9468.548906999986, "eligible_miss": 0.0, "miss": 8.0, "model": 608.0, "overflow": 8.0, "padding": 3.0, "tokens": 16480.0 }, { "bucket": 432.0, "duration_ms": 6951.234554999997, "eligible_miss": 0.0, "miss": 10.0, "model": 442.0, "overflow": 10.0, "padding": 0.0, "tokens": 18453.0 }, { "bucket": 938.0, "duration_ms": 6602.597068, "eligible_miss": 0.0, "miss": 3.0, "model": 654.0, "overflow": 3.0, "padding": 11.0, "tokens": 5931.0 }, { "duration_ms": 9777.494176999999, "eligible_miss": 0.0, "miss": 22.0, "model": 22.0, "overflow": 22.0, "tokens": 43529.0 }, { "bucket": 1010.0, "duration_ms": 10071.462241000005, "eligible_miss": 0.0, "miss": 13.0, "model": 281.0, "overflow": 13.0, "padding": 188.0, "tokens": 27103.0 }, { "bucket": 958.0, "duration_ms": 8959.625635999993, "eligible_miss": 0.0, "miss": 7.0, "model": 528.0, "overflow": 7.0, "padding": 92.0, "tokens": 13677.0 }, { "bucket": 444.0, "duration_ms": 4595.177759999996, "eligible_miss": 0.0, "miss": 3.0, "model": 447.0, "overflow": 3.0, "padding": 0.0, "tokens": 6068.0 }, { "bucket": 255.0, "duration_ms": 7323.852219999997, "eligible_miss": 0.0, "miss": 12.0, "model": 267.0, "overflow": 12.0, "padding": 0.0, "tokens": 24473.0 }, { "bucket": 927.0, "duration_ms": 7674.425592000002, "eligible_miss": 0.0, "miss": 3.0, "model": 587.0, "overflow": 3.0, "padding": 0.0, "tokens": 6033.0 }, { "bucket": 255.0, "duration_ms": 4658.851812999998, "eligible_miss": 0.0, "miss": 8.0, "model": 263.0, "overflow": 8.0, "padding": 0.0, "tokens": 15325.0 }, { "bucket": 952.0, "duration_ms": 9628.718707000005, "eligible_miss": 0.0, "miss": 14.0, "model": 323.0, "overflow": 14.0, "padding": 45.0, "tokens": 27847.0 }, { "bucket": 1378.0, "duration_ms": 5780.386532000003, "eligible_miss": 0.0, "miss": 3.0, "model": 462.0, "overflow": 3.0, "padding": 13.0, "tokens": 7509.0 }, { "bucket": 698.0, "duration_ms": 6068.889615000002, "eligible_miss": 0.0, "miss": 5.0, "model": 545.0, "overflow": 5.0, "padding": 6.0, "tokens": 10027.0 }, { "bucket": 562.0, "duration_ms": 8098.781943, "eligible_miss": 0.0, "miss": 11.0, "model": 494.0, "overflow": 11.0, "padding": 7.0, "tokens": 23083.0 }, { "bucket": 791.0, "duration_ms": 9644.798028000012, "eligible_miss": 0.0, "miss": 8.0, "model": 375.0, "overflow": 8.0, "padding": 85.0, "tokens": 15246.0 }, { "bucket": 466.0, "duration_ms": 6499.454319999998, "eligible_miss": 0.0, "miss": 7.0, "model": 473.0, "overflow": 7.0, "padding": 0.0, "tokens": 14168.0 }, { "bucket": 447.0, "duration_ms": 10338.326678999998, "eligible_miss": 0.0, "miss": 16.0, "model": 354.0, "overflow": 16.0, "padding": 5.0, "tokens": 32959.0 }, { "bucket": 905.0, "duration_ms": 6872.5209749999885, "eligible_miss": 0.0, "miss": 1.0, "model": 637.0, "overflow": 1.0, "padding": 4.0, "tokens": 1848.0 }, { "bucket": 520.0, "duration_ms": 2768.948879, "eligible_miss": 0.0, "miss": 1.0, "model": 298.0, "overflow": 1.0, "padding": 1.0, "tokens": 1741.0 } ], "clean": { "admitted": 107, "completed": 107, "completed_throughput_rps": 0.44583333333333336, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 933292, "offered_rps": 0.44583333333333336, "output_tokens": 24329, "start_s": 60.0 }, "config": "C01", "drain_quarantined": false, "drain_seconds": 0.3054194079886656, "latency_s": { "e2e": { "mean": 3.4583488524498125, "n": 107, "p50": 2.139935596002033, "p95": 9.892479610099684, "p99": 14.278773261667808 }, "tpot": { "mean": 0.010096695599975438, "n": 107, "p50": 0.00563074907849488, "p95": 0.029468602368621807, "p99": 0.04342289214143664 }, "ttft": { "mean": 1.0536771315690152, "n": 107, "p50": 0.7089335940254387, "p95": 3.353996323794126, "p99": 4.558524873343412 } }, "layer1": { "decode_tokens": 24222, "kv_usage_max": 0.3808813342569404, "kv_usage_mean": 0.044735391515669486, "mode_counts": { "FULL": 16854, "NONE": 585, "PIECEWISE": 28 }, "mode_shares": { "FULL": 0.9649052498998111, "NONE": 0.03349172725711341, "PIECEWISE": 0.0016030228430755139 }, "preemptions": 0, "prefill_tokens": 916316, "prefix_query_hit_ratio": 0.018189376958122432, "queue_waiting_max": 1, "queue_waiting_mean": 0.0010877655006583844, "records_all": 24251, "records_clean": 17467, "requests_per_step": { "mean": 1.4158126753306235, "n": 17467, "p50": 1.0, "p95": 3.0, "p99": 6.0 }, "scheduled_tokens_per_step": { "mean": 53.84656781359134, "n": 17467, "p50": 1.0, "p95": 4.0, "p99": 2048.0 }, "step_duration_ms": { "mean": 21.36354231757028, "n": 17467, "p50": 9.592219, "p95": 28.20071580000003, "p99": 409.62446344 }, "token_efficiency_per_ms": 2.520488737923657 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P10", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 0.45, "clean_c_waiting_median": 0.0, "completion_rate_rps": 0.8, "completion_rate_within_10pct": false, "tail_end_s": 338.4903358910233, "tail_start_s": 328.4903358910233, "valid": false, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 0.45, "clean_c_waiting_median": 0.0, "completion_rate_rps": 0.9, "completion_rate_within_10pct": false, "tail_end_s": 381.45741498301504, "tail_start_s": 371.45741498301504, "valid": false, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 107, "run_dir": "runs/phase3/primary/P10-C01/moderate", "run_id": "P10-C01-moderate", "trace_files": 2, "waste": { "R128": 0.7047173851989379, "R32": 0.6764453342592629, "R64": 0.6923054365307624, "bucket_slack": 0.0533824348579563, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.0270301423549075, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 226, "moe_layer_cv": null, "overflow_rate": 0.0270301423549075, "padded_tokens_per_useful_token": 0.0018340566781990732, "padding_fraction": 0.0533824348579563 } }, "P10-C01-saturation": { "blocks": [ { "duration_ms": 9618.323389999998, "eligible_miss": 0.0, "miss": 17.0, "model": 17.0, "overflow": 17.0, "tokens": 34816.0 }, { "bucket": 568.0, "duration_ms": 9715.450135999998, "eligible_miss": 0.0, "miss": 15.0, "model": 32.0, "overflow": 15.0, "padding": 83.0, "tokens": 31205.0 }, { "bucket": 2416.0, "duration_ms": 10303.149564000001, "eligible_miss": 0.0, "miss": 11.0, "model": 88.0, "overflow": 11.0, "padding": 471.0, "tokens": 24119.0 }, { "duration_ms": 9830.213772, "eligible_miss": 0.0, "miss": 18.0, "model": 18.0, "overflow": 18.0, "tokens": 36864.0 }, { "duration_ms": 10602.143477999998, "eligible_miss": 0.0, "miss": 22.0, "model": 22.0, "overflow": 22.0, "tokens": 45056.0 }, { "duration_ms": 9267.446006, "eligible_miss": 0.0, "miss": 17.0, "model": 17.0, "overflow": 17.0, "tokens": 33346.0 }, { "bucket": 320.0, "duration_ms": 10856.284119, "eligible_miss": 0.0, "miss": 15.0, "model": 35.0, "overflow": 15.0, "padding": 41.0, "tokens": 30939.0 }, { "bucket": 256.0, "duration_ms": 9228.995142999998, "eligible_miss": 0.0, "miss": 15.0, "model": 31.0, "overflow": 15.0, "padding": 46.0, "tokens": 30912.0 }, { "duration_ms": 10118.542377999998, "eligible_miss": 0.0, "miss": 15.0, "model": 15.0, "overflow": 15.0, "tokens": 30720.0 }, { "duration_ms": 10201.908828999998, "eligible_miss": 0.0, "miss": 18.0, "model": 18.0, "overflow": 18.0, "tokens": 36864.0 }, { "duration_ms": 9753.736368, "eligible_miss": 0.0, "miss": 22.0, "model": 22.0, "overflow": 22.0, "tokens": 44505.0 }, { "bucket": 152.0, "duration_ms": 9841.631798, "eligible_miss": 0.0, "miss": 22.0, "model": 30.0, "overflow": 22.0, "padding": 16.0, "tokens": 44528.0 }, { "bucket": 1512.0, "duration_ms": 10504.794488, "eligible_miss": 0.0, "miss": 13.0, "model": 76.0, "overflow": 13.0, "padding": 311.0, "tokens": 27062.0 }, { "bucket": 48.0, "duration_ms": 9442.621208999999, "eligible_miss": 0.0, "miss": 19.0, "model": 21.0, "overflow": 19.0, "padding": 6.0, "tokens": 37606.0 }, { "bucket": 760.0, "duration_ms": 10248.626628999997, "eligible_miss": 0.0, "miss": 22.0, "model": 47.0, "overflow": 22.0, "padding": 108.0, "tokens": 44547.0 }, { "bucket": 1240.0, "duration_ms": 10165.940051, "eligible_miss": 0.0, "miss": 15.0, "model": 47.0, "overflow": 15.0, "padding": 99.0, "tokens": 31861.0 }, { "duration_ms": 9696.808636, "eligible_miss": 0.0, "miss": 23.0, "model": 23.0, "overflow": 23.0, "tokens": 47104.0 }, { "duration_ms": 10186.123948, "eligible_miss": 0.0, "miss": 19.0, "model": 19.0, "overflow": 19.0, "tokens": 38912.0 }, { "duration_ms": 10415.876993000002, "eligible_miss": 0.0, "miss": 22.0, "model": 22.0, "overflow": 22.0, "tokens": 44975.0 }, { "bucket": 1760.0, "duration_ms": 9292.007447999998, "eligible_miss": 0.0, "miss": 15.0, "model": 59.0, "overflow": 15.0, "padding": 53.0, "tokens": 31127.0 }, { "bucket": 720.0, "duration_ms": 10396.926209, "eligible_miss": 0.0, "miss": 20.0, "model": 38.0, "overflow": 20.0, "padding": 79.0, "tokens": 41152.0 }, { "duration_ms": 10035.738295999998, "eligible_miss": 0.0, "miss": 16.0, "model": 16.0, "overflow": 16.0, "tokens": 31763.0 }, { "bucket": 1088.0, "duration_ms": 10139.922182, "eligible_miss": 0.0, "miss": 18.0, "model": 50.0, "overflow": 18.0, "padding": 51.0, "tokens": 36827.0 }, { "bucket": 1000.0, "duration_ms": 9732.766099999997, "eligible_miss": 0.0, "miss": 14.0, "model": 38.0, "overflow": 14.0, "padding": 161.0, "tokens": 29511.0 }, { "bucket": 192.0, "duration_ms": 10131.727447999998, "eligible_miss": 0.0, "miss": 18.0, "model": 23.0, "overflow": 18.0, "padding": 28.0, "tokens": 36374.0 }, { "bucket": 144.0, "duration_ms": 9822.238614, "eligible_miss": 0.0, "miss": 24.0, "model": 26.0, "overflow": 24.0, "padding": 5.0, "tokens": 49291.0 }, { "duration_ms": 10355.003429999999, "eligible_miss": 0.0, "miss": 20.0, "model": 20.0, "overflow": 20.0, "tokens": 40960.0 }, { "bucket": 1312.0, "duration_ms": 9328.351725, "eligible_miss": 0.0, "miss": 12.0, "model": 53.0, "overflow": 12.0, "padding": 170.0, "tokens": 24406.0 }, { "bucket": 640.0, "duration_ms": 10598.633892, "eligible_miss": 0.0, "miss": 15.0, "model": 35.0, "overflow": 15.0, "padding": 107.0, "tokens": 31253.0 }, { "duration_ms": 9896.93457, "eligible_miss": 0.0, "miss": 22.0, "model": 22.0, "overflow": 22.0, "tokens": 45056.0 }, { "bucket": 920.0, "duration_ms": 9851.330482999998, "eligible_miss": 0.0, "miss": 18.0, "model": 49.0, "overflow": 18.0, "padding": 157.0, "tokens": 36871.0 }, { "bucket": 312.0, "duration_ms": 9662.383065000002, "eligible_miss": 0.0, "miss": 17.0, "model": 30.0, "overflow": 17.0, "padding": 6.0, "tokens": 34549.0 }, { "bucket": 384.0, "duration_ms": 10609.498962, "eligible_miss": 0.0, "miss": 21.0, "model": 37.0, "overflow": 21.0, "padding": 17.0, "tokens": 43375.0 }, { "duration_ms": 9741.637745000002, "eligible_miss": 0.0, "miss": 18.0, "model": 18.0, "overflow": 18.0, "tokens": 36864.0 }, { "duration_ms": 9892.446897000002, "eligible_miss": 0.0, "miss": 22.0, "model": 22.0, "overflow": 22.0, "tokens": 45056.0 }, { "bucket": 896.0, "duration_ms": 9733.218633999997, "eligible_miss": 0.0, "miss": 18.0, "model": 46.0, "overflow": 18.0, "padding": 196.0, "tokens": 36052.0 }, { "bucket": 984.0, "duration_ms": 10332.206858000001, "eligible_miss": 0.0, "miss": 20.0, "model": 51.0, "overflow": 20.0, "padding": 210.0, "tokens": 41734.0 }, { "bucket": 96.0, "duration_ms": 10533.172222, "eligible_miss": 0.0, "miss": 22.0, "model": 25.0, "overflow": 22.0, "padding": 10.0, "tokens": 43712.0 }, { "bucket": 448.0, "duration_ms": 9116.097409999998, "eligible_miss": 0.0, "miss": 14.0, "model": 28.0, "overflow": 14.0, "padding": 42.0, "tokens": 27607.0 }, { "bucket": 256.0, "duration_ms": 10697.825888, "eligible_miss": 0.0, "miss": 24.0, "model": 32.0, "overflow": 24.0, "padding": 28.0, "tokens": 49380.0 }, { "bucket": 640.0, "duration_ms": 9922.849348, "eligible_miss": 0.0, "miss": 18.0, "model": 38.0, "overflow": 18.0, "padding": 97.0, "tokens": 37145.0 }, { "bucket": 480.0, "duration_ms": 9694.890612999998, "eligible_miss": 0.0, "miss": 19.0, "model": 34.0, "overflow": 19.0, "padding": 90.0, "tokens": 38612.0 }, { "duration_ms": 9985.187363, "eligible_miss": 0.0, "miss": 20.0, "model": 20.0, "overflow": 20.0, "tokens": 40960.0 }, { "bucket": 1728.0, "duration_ms": 10054.963302000002, "eligible_miss": 0.0, "miss": 14.0, "model": 68.0, "overflow": 14.0, "padding": 299.0, "tokens": 29357.0 }, { "bucket": 160.0, "duration_ms": 9795.101537999999, "eligible_miss": 0.0, "miss": 22.0, "model": 27.0, "overflow": 22.0, "padding": 31.0, "tokens": 44721.0 }, { "bucket": 128.0, "duration_ms": 10214.997361, "eligible_miss": 0.0, "miss": 19.0, "model": 23.0, "overflow": 19.0, "padding": 17.0, "tokens": 38461.0 }, { "bucket": 448.0, "duration_ms": 9722.990461, "eligible_miss": 0.0, "miss": 18.0, "model": 32.0, "overflow": 18.0, "padding": 7.0, "tokens": 35935.0 }, { "duration_ms": 10366.926333999998, "eligible_miss": 0.0, "miss": 24.0, "model": 24.0, "overflow": 24.0, "tokens": 49152.0 } ], "clean": { "admitted": 178, "completed": 178, "completed_throughput_rps": 0.7416666666666667, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 1755158, "offered_rps": 0.7416666666666667, "output_tokens": 40658, "start_s": 60.0 }, "config": "C01", "drain_quarantined": false, "drain_seconds": 288.6191079240234, "latency_s": { "e2e": { "mean": 183.04354939324844, "n": 178, "p50": 186.8344520800165, "p95": 290.3771271756501, "p99": 296.9446104261672 }, "tpot": { "mean": 0.14786293761943992, "n": 178, "p50": 0.14534626581766596, "p95": 0.17603060793336645, "p99": 0.22781931117242266 }, "ttft": { "mean": 149.49741162677012, "n": 178, "p50": 150.95995998900617, "p95": 258.07463337168736, "p99": 280.9327837695714 } }, "layer1": { "decode_tokens": 39630, "kv_usage_max": 1.0, "kv_usage_mean": 0.9423858731719604, "mode_counts": { "FULL": 697, "NONE": 882, "PIECEWISE": 5 }, "mode_shares": { "FULL": 0.44002525252525254, "NONE": 0.5568181818181818, "PIECEWISE": 0.0031565656565656565 }, "preemptions": 1, "prefill_tokens": 1763574, "prefix_query_hit_ratio": 0.004381548750661162, "queue_waiting_max": 244, "queue_waiting_mean": 230.1294191919192, "records_all": 4742, "records_clean": 1584, "requests_per_step": { "mean": 25.63888888888889, "n": 1584, "p50": 26.0, "p95": 35.0, "p99": 39.0 }, "scheduled_tokens_per_step": { "mean": 1138.3863636363637, "n": 1584, "p50": 2048.0, "p95": 2048.0, "p99": 2048.0 }, "step_duration_ms": { "mean": 302.8135046294192, "n": 1584, "p50": 324.637002, "p95": 706.7920114499998, "p99": 844.95236557 }, "token_efficiency_per_ms": 3.7593645799566042 }, "layer2_missing_after_controller_cleanup": true, "load": "saturation", "pattern": "P10", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 0.8, "clean_c_waiting_median": 229.0, "completion_rate_rps": 0.7, "completion_rate_within_10pct": false, "tail_end_s": 368.55468072599615, "tail_start_s": 358.55468072599615, "valid": false, "waiting_median": 219.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 0.8, "clean_c_waiting_median": 229.0, "completion_rate_rps": 0.9, "completion_rate_within_10pct": false, "tail_end_s": 420.6437278209778, "tail_start_s": 410.6437278209778, "valid": false, "waiting_median": 234.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 178, "run_dir": "runs/phase3/primary/P10-C01/saturation", "run_id": "P10-C01-saturation", "trace_files": 0, "waste": { "R128": 0.7047173851989379, "R32": 0.6764453342592629, "R64": 0.6923054365307624, "bucket_slack": 0.13822246455834242, "eligible_miss_rate": 0.0, "graph_miss_rate": 0.5568181818181818, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.5568181818181818, "padded_tokens_per_useful_token": 0.0016869971450817545, "padding_fraction": 0.13822246455834242 } }, "P10-C10-moderate": { "blocks": [ { "bucket": 343.0, "duration_ms": 10106.476507000005, "eligible_miss": 0.0, "miss": 5.0, "model": 347.0, "overflow": 5.0, "padding": 0.0, "tokens": 34424.0 }, { "bucket": 4.0, "duration_ms": 11007.921244, "eligible_miss": 0.0, "miss": 7.0, "model": 8.0, "overflow": 7.0, "padding": 1.0, "tokens": 53699.0 }, { "bucket": 1136.0, "duration_ms": 7384.894006999999, "eligible_miss": 0.0, "miss": 3.0, "model": 145.0, "overflow": 3.0, "padding": 339.0, "tokens": 16975.0 }, { "bucket": 1018.0, "duration_ms": 11292.837419000001, "eligible_miss": 0.0, "miss": 6.0, "model": 194.0, "overflow": 6.0, "padding": 203.0, "tokens": 43013.0 }, { "bucket": 96.0, "duration_ms": 8682.53226, "eligible_miss": 1.0, "miss": 6.0, "model": 26.0, "overflow": 5.0, "padding": 28.0, "tokens": 29653.0 }, { "bucket": 1386.0, "duration_ms": 7021.152411000001, "eligible_miss": 0.0, "miss": 3.0, "model": 317.0, "overflow": 3.0, "padding": 287.0, "tokens": 10081.0 }, { "bucket": 509.0, "duration_ms": 9115.488792000006, "eligible_miss": 0.0, "miss": 4.0, "model": 513.0, "overflow": 4.0, "padding": 0.0, "tokens": 27533.0 }, { "bucket": 4.0, "duration_ms": 8336.767972, "eligible_miss": 0.0, "miss": 4.0, "model": 5.0, "overflow": 4.0, "padding": 1.0, "tokens": 28327.0 }, { "bucket": 828.0, "duration_ms": 9504.892607000002, "eligible_miss": 0.0, "miss": 5.0, "model": 162.0, "overflow": 5.0, "padding": 101.0, "tokens": 30693.0 }, { "bucket": 936.0, "duration_ms": 9976.587113999994, "eligible_miss": 0.0, "miss": 4.0, "model": 136.0, "overflow": 4.0, "padding": 184.0, "tokens": 27456.0 }, { "bucket": 1212.0, "duration_ms": 9979.223648999996, "eligible_miss": 1.0, "miss": 5.0, "model": 262.0, "overflow": 4.0, "padding": 192.0, "tokens": 28329.0 }, { "bucket": 472.0, "duration_ms": 7446.108408999998, "eligible_miss": 0.0, "miss": 4.0, "model": 377.0, "overflow": 4.0, "padding": 19.0, "tokens": 20125.0 }, { "bucket": 391.0, "duration_ms": 8153.021131000002, "eligible_miss": 0.0, "miss": 5.0, "model": 315.0, "overflow": 5.0, "padding": 0.0, "tokens": 26659.0 }, { "bucket": 739.0, "duration_ms": 7842.656145999993, "eligible_miss": 0.0, "miss": 3.0, "model": 538.0, "overflow": 3.0, "padding": 0.0, "tokens": 14193.0 }, { "bucket": 408.0, "duration_ms": 8552.172508000003, "eligible_miss": 0.0, "miss": 5.0, "model": 413.0, "overflow": 5.0, "padding": 0.0, "tokens": 33189.0 }, { "bucket": 874.0, "duration_ms": 7561.893929999997, "eligible_miss": 0.0, "miss": 2.0, "model": 477.0, "overflow": 2.0, "padding": 12.0, "tokens": 9802.0 }, { "bucket": 302.0, "duration_ms": 4306.8247440000005, "eligible_miss": 1.0, "miss": 4.0, "model": 306.0, "overflow": 3.0, "padding": 0.0, "tokens": 12522.0 }, { "bucket": 646.0, "duration_ms": 8740.812153000004, "eligible_miss": 1.0, "miss": 3.0, "model": 495.0, "overflow": 2.0, "padding": 0.0, "tokens": 17456.0 }, { "bucket": 328.0, "duration_ms": 9669.982888, "eligible_miss": 0.0, "miss": 5.0, "model": 324.0, "overflow": 5.0, "padding": 0.0, "tokens": 32644.0 }, { "bucket": 812.0, "duration_ms": 6619.143540000003, "eligible_miss": 1.0, "miss": 3.0, "model": 513.0, "overflow": 2.0, "padding": 24.0, "tokens": 7524.0 }, { "bucket": 198.0, "duration_ms": 1584.5358729999998, "eligible_miss": 1.0, "miss": 1.0, "model": 176.0, "overflow": 0.0, "padding": 5.0, "tokens": 390.0 }, { "bucket": 499.0, "duration_ms": 8041.176958999996, "eligible_miss": 0.0, "miss": 5.0, "model": 504.0, "overflow": 5.0, "padding": 0.0, "tokens": 24697.0 }, { "bucket": 536.0, "duration_ms": 6431.412983999996, "eligible_miss": 2.0, "miss": 3.0, "model": 530.0, "overflow": 1.0, "padding": 0.0, "tokens": 9315.0 }, { "bucket": 289.0, "duration_ms": 9811.863633000004, "eligible_miss": 0.0, "miss": 6.0, "model": 217.0, "overflow": 6.0, "padding": 1.0, "tokens": 41862.0 }, { "bucket": 1109.0, "duration_ms": 9629.157217999988, "eligible_miss": 0.0, "miss": 3.0, "model": 638.0, "overflow": 3.0, "padding": 111.0, "tokens": 15744.0 }, { "bucket": 538.0, "duration_ms": 8930.29845700001, "eligible_miss": 0.0, "miss": 4.0, "model": 448.0, "overflow": 4.0, "padding": 3.0, "tokens": 26534.0 }, { "bucket": 607.0, "duration_ms": 7727.710782000003, "eligible_miss": 0.0, "miss": 3.0, "model": 537.0, "overflow": 3.0, "padding": 0.0, "tokens": 18628.0 }, { "bucket": 710.0, "duration_ms": 7073.704011, "eligible_miss": 0.0, "miss": 2.0, "model": 699.0, "overflow": 2.0, "padding": 0.0, "tokens": 5992.0 }, { "bucket": 169.0, "duration_ms": 9870.707891999999, "eligible_miss": 0.0, "miss": 7.0, "model": 50.0, "overflow": 7.0, "padding": 42.0, "tokens": 43650.0 }, { "bucket": 836.0, "duration_ms": 10003.146918, "eligible_miss": 0.0, "miss": 5.0, "model": 203.0, "overflow": 5.0, "padding": 149.0, "tokens": 31768.0 }, { "bucket": 1200.0, "duration_ms": 8354.661415000008, "eligible_miss": 0.0, "miss": 3.0, "model": 574.0, "overflow": 3.0, "padding": 173.0, "tokens": 10969.0 }, { "bucket": 564.0, "duration_ms": 5582.916378000002, "eligible_miss": 0.0, "miss": 2.0, "model": 566.0, "overflow": 2.0, "padding": 0.0, "tokens": 5935.0 }, { "bucket": 454.0, "duration_ms": 9035.325433000004, "eligible_miss": 0.0, "miss": 4.0, "model": 254.0, "overflow": 4.0, "padding": 1.0, "tokens": 28016.0 }, { "bucket": 560.0, "duration_ms": 5052.833035999991, "eligible_miss": 1.0, "miss": 2.0, "model": 558.0, "overflow": 1.0, "padding": 0.0, "tokens": 1534.0 }, { "bucket": 259.0, "duration_ms": 9378.153805999998, "eligible_miss": 1.0, "miss": 7.0, "model": 203.0, "overflow": 6.0, "padding": 0.0, "tokens": 41925.0 }, { "bucket": 837.0, "duration_ms": 6503.318629000009, "eligible_miss": 1.0, "miss": 2.0, "model": 435.0, "overflow": 1.0, "padding": 75.0, "tokens": 7678.0 }, { "bucket": 616.0, "duration_ms": 6539.7740289999965, "eligible_miss": 0.0, "miss": 2.0, "model": 603.0, "overflow": 2.0, "padding": 1.0, "tokens": 10089.0 }, { "bucket": 509.0, "duration_ms": 10607.03604, "eligible_miss": 0.0, "miss": 5.0, "model": 514.0, "overflow": 5.0, "padding": 0.0, "tokens": 35398.0 }, { "bucket": 880.0, "duration_ms": 7213.780934000007, "eligible_miss": 0.0, "miss": 3.0, "model": 393.0, "overflow": 3.0, "padding": 118.0, "tokens": 3015.0 }, { "bucket": 482.0, "duration_ms": 8018.256782999996, "eligible_miss": 0.0, "miss": 5.0, "model": 480.0, "overflow": 5.0, "padding": 0.0, "tokens": 24213.0 }, { "bucket": 751.0, "duration_ms": 9984.175938, "eligible_miss": 0.0, "miss": 3.0, "model": 438.0, "overflow": 3.0, "padding": 5.0, "tokens": 23234.0 }, { "bucket": 752.0, "duration_ms": 6134.946822999995, "eligible_miss": 0.0, "miss": 2.0, "model": 635.0, "overflow": 2.0, "padding": 21.0, "tokens": 2900.0 }, { "bucket": 272.0, "duration_ms": 3775.7959439999972, "eligible_miss": 2.0, "miss": 3.0, "model": 275.0, "overflow": 1.0, "padding": 0.0, "tokens": 9101.0 }, { "bucket": 595.0, "duration_ms": 8498.819438, "eligible_miss": 0.0, "miss": 4.0, "model": 570.0, "overflow": 4.0, "padding": 0.0, "tokens": 21647.0 }, { "bucket": 400.0, "duration_ms": 10498.661573000001, "eligible_miss": 0.0, "miss": 5.0, "model": 390.0, "overflow": 5.0, "padding": 0.0, "tokens": 39452.0 }, { "bucket": 700.0, "duration_ms": 9937.671109000004, "eligible_miss": 0.0, "miss": 4.0, "model": 174.0, "overflow": 4.0, "padding": 83.0, "tokens": 28790.0 }, { "bucket": 188.0, "duration_ms": 10682.796628, "eligible_miss": 1.0, "miss": 6.0, "model": 53.0, "overflow": 5.0, "padding": 0.0, "tokens": 37936.0 }, { "bucket": 1652.0, "duration_ms": 7574.382696000001, "eligible_miss": 1.0, "miss": 2.0, "model": 234.0, "overflow": 1.0, "padding": 431.0, "tokens": 9741.0 } ], "clean": { "admitted": 117, "completed": 114, "completed_throughput_rps": 0.475, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 1011895, "offered_rps": 0.4875, "output_tokens": 26177, "start_s": 60.0 }, "config": "C10", "drain_quarantined": false, "drain_seconds": 1.0034805840114132, "latency_s": { "e2e": { "mean": 4.036499573850163, "n": 114, "p50": 2.565201995501411, "p95": 11.757720911737124, "p99": 15.403192080657472 }, "tpot": { "mean": 0.012512976698821513, "n": 114, "p50": 0.006702121849636516, "p95": 0.03670983474116142, "p99": 0.04342372289472191 }, "ttft": { "mean": 1.008607643877775, "n": 114, "p50": 0.6484979435044806, "p95": 3.168752788902201, "p99": 4.3141448924437285 } }, "layer1": { "decode_tokens": 26784, "kv_usage_max": 0.35747826955739836, "kv_usage_mean": 0.04747642230487483, "mode_counts": { "FULL": 17025, "NONE": 293, "PIECEWISE": 10 }, "mode_shares": { "FULL": 0.9825138504155124, "NONE": 0.016909048938134812, "PIECEWISE": 0.0005771006463527239 }, "preemptions": 0, "prefill_tokens": 1037666, "prefix_query_hit_ratio": 0.01670807677073206, "queue_waiting_max": 1, "queue_waiting_mean": 5.771006463527239e-05, "records_all": 25426, "records_clean": 17328, "requests_per_step": { "mean": 1.5573060941828254, "n": 17328, "p50": 1.0, "p95": 4.0, "p99": 6.0 }, "scheduled_tokens_per_step": { "mean": 61.4294783010157, "n": 17328, "p50": 1.0, "p95": 5.0, "p99": 560.6799999999494 }, "step_duration_ms": { "mean": 22.724977538665744, "n": 17328, "p50": 9.6194405, "p95": 25.861211249999997, "p99": 402.42142650999864 }, "token_efficiency_per_ms": 2.7031700337875195 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P10", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 0.4, "clean_c_waiting_median": 0.0, "completion_rate_rps": 0.3, "completion_rate_within_10pct": false, "tail_end_s": 331.677197498997, "tail_start_s": 321.677197498997, "valid": false, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 0.4, "clean_c_waiting_median": 0.0, "completion_rate_rps": 0.6, "completion_rate_within_10pct": false, "tail_end_s": 364.01766435598256, "tail_start_s": 354.01766435598256, "valid": false, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 114, "run_dir": "runs/phase3/primary/P10-C10/moderate", "run_id": "P10-C10-moderate", "trace_files": 2, "waste": { "R128": 0.7047173851989379, "R32": 0.6764453342592629, "R64": 0.6923054365307624, "bucket_slack": 0.07714860592124173, "eligible_miss_rate": 0.0008708778448676265, "graph_miss_rate": 0.010973060845332094, "mixed_interference": null, "mixed_supported_steps": 0, "mixed_total_steps": 114, "moe_layer_cv": null, "overflow_rate": 0.010102183000464468, "padded_tokens_per_useful_token": 0.0024519705011978015, "padding_fraction": 0.08815780585016551 } }, "P10-C10-saturation": { "blocks": [ { "bucket": 6616.0, "duration_ms": 9902.418747000002, "eligible_miss": 3.0, "miss": 5.0, "model": 117.0, "overflow": 2.0, "padding": 499.0, "tokens": 8832.0 }, { "bucket": 4656.0, "duration_ms": 11073.679255, "eligible_miss": 0.0, "miss": 7.0, "model": 104.0, "overflow": 7.0, "padding": 133.0, "tokens": 34294.0 }, { "duration_ms": 9774.869166999999, "eligible_miss": 0.0, "miss": 8.0, "model": 8.0, "overflow": 8.0, "tokens": 65536.0 }, { "bucket": 112.0, "duration_ms": 9892.910486, "eligible_miss": 0.0, "miss": 8.0, "model": 10.0, "overflow": 8.0, "padding": 2.0, "tokens": 64002.0 }, { "duration_ms": 10001.235723, "eligible_miss": 0.0, "miss": 9.0, "model": 9.0, "overflow": 9.0, "tokens": 73728.0 }, { "duration_ms": 10119.018779000002, "eligible_miss": 0.0, "miss": 8.0, "model": 8.0, "overflow": 8.0, "tokens": 65536.0 }, { "bucket": 4920.0, "duration_ms": 9125.751893, "eligible_miss": 0.0, "miss": 2.0, "model": 81.0, "overflow": 2.0, "padding": 287.0, "tokens": 19456.0 }, { "bucket": 5600.0, "duration_ms": 9984.559546000002, "eligible_miss": 0.0, "miss": 3.0, "model": 103.0, "overflow": 3.0, "padding": 320.0, "tokens": 19133.0 }, { "bucket": 1928.0, "duration_ms": 12199.917546000002, "eligible_miss": 0.0, "miss": 6.0, "model": 43.0, "overflow": 6.0, "padding": 129.0, "tokens": 48899.0 }, { "duration_ms": 9820.404919, "eligible_miss": 0.0, "miss": 5.0, "model": 5.0, "overflow": 5.0, "tokens": 40960.0 }, { "bucket": 32.0, "duration_ms": 8602.427712, "eligible_miss": 0.0, "miss": 4.0, "model": 5.0, "overflow": 4.0, "padding": 0.0, "tokens": 29474.0 }, { "bucket": 32.0, "duration_ms": 10829.544716999999, "eligible_miss": 0.0, "miss": 7.0, "model": 8.0, "overflow": 7.0, "padding": 5.0, "tokens": 49947.0 }, { "duration_ms": 11234.986391, "eligible_miss": 0.0, "miss": 5.0, "model": 5.0, "overflow": 5.0, "tokens": 40960.0 }, { "duration_ms": 8382.891783, "eligible_miss": 0.0, "miss": 5.0, "model": 5.0, "overflow": 5.0, "tokens": 40960.0 }, { "duration_ms": 9916.166873999999, "eligible_miss": 0.0, "miss": 6.0, "model": 6.0, "overflow": 6.0, "tokens": 42794.0 }, { "bucket": 1472.0, "duration_ms": 10955.237687999997, "eligible_miss": 0.0, "miss": 5.0, "model": 67.0, "overflow": 5.0, "padding": 420.0, "tokens": 34910.0 }, { "bucket": 472.0, "duration_ms": 7994.8781, "eligible_miss": 0.0, "miss": 3.0, "model": 23.0, "overflow": 3.0, "padding": 133.0, "tokens": 24594.0 }, { "bucket": 896.0, "duration_ms": 10001.742973000004, "eligible_miss": 0.0, "miss": 4.0, "model": 60.0, "overflow": 4.0, "padding": 55.0, "tokens": 32428.0 }, { "bucket": 1040.0, "duration_ms": 11356.648647999999, "eligible_miss": 0.0, "miss": 5.0, "model": 70.0, "overflow": 5.0, "padding": 67.0, "tokens": 33503.0 }, { "bucket": 80.0, "duration_ms": 9773.165826999999, "eligible_miss": 0.0, "miss": 7.0, "model": 12.0, "overflow": 7.0, "padding": 6.0, "tokens": 57418.0 }, { "bucket": 16.0, "duration_ms": 9263.606479999999, "eligible_miss": 0.0, "miss": 6.0, "model": 7.0, "overflow": 6.0, "padding": 0.0, "tokens": 39803.0 }, { "bucket": 136.0, "duration_ms": 11027.643027, "eligible_miss": 0.0, "miss": 7.0, "model": 13.0, "overflow": 7.0, "padding": 35.0, "tokens": 57445.0 }, { "bucket": 1032.0, "duration_ms": 9844.611378999998, "eligible_miss": 0.0, "miss": 5.0, "model": 48.0, "overflow": 5.0, "padding": 259.0, "tokens": 37190.0 }, { "bucket": 504.0, "duration_ms": 10220.950637, "eligible_miss": 0.0, "miss": 5.0, "model": 26.0, "overflow": 5.0, "padding": 106.0, "tokens": 36540.0 }, { "bucket": 1032.0, "duration_ms": 8496.597829000002, "eligible_miss": 0.0, "miss": 4.0, "model": 47.0, "overflow": 4.0, "padding": 217.0, "tokens": 29147.0 }, { "bucket": 1320.0, "duration_ms": 9977.614238999997, "eligible_miss": 0.0, "miss": 4.0, "model": 59.0, "overflow": 4.0, "padding": 276.0, "tokens": 31867.0 }, { "bucket": 720.0, "duration_ms": 10088.512911999998, "eligible_miss": 0.0, "miss": 6.0, "model": 36.0, "overflow": 6.0, "padding": 151.0, "tokens": 38179.0 }, { "bucket": 384.0, "duration_ms": 12066.516112, "eligible_miss": 0.0, "miss": 6.0, "model": 22.0, "overflow": 6.0, "padding": 75.0, "tokens": 49461.0 }, { "duration_ms": 10250.579179999999, "eligible_miss": 0.0, "miss": 5.0, "model": 5.0, "overflow": 5.0, "tokens": 40960.0 }, { "bucket": 112.0, "duration_ms": 10331.163991999998, "eligible_miss": 0.0, "miss": 6.0, "model": 11.0, "overflow": 6.0, "padding": 28.0, "tokens": 41306.0 }, { "duration_ms": 7934.342012, "eligible_miss": 0.0, "miss": 5.0, "model": 5.0, "overflow": 5.0, "tokens": 35929.0 }, { "bucket": 624.0, "duration_ms": 9344.787628000002, "eligible_miss": 0.0, "miss": 4.0, "model": 30.0, "overflow": 4.0, "padding": 182.0, "tokens": 27843.0 }, { "bucket": 792.0, "duration_ms": 10257.251678999999, "eligible_miss": 0.0, "miss": 6.0, "model": 47.0, "overflow": 6.0, "padding": 120.0, "tokens": 36425.0 }, { "bucket": 912.0, "duration_ms": 12426.491586999999, "eligible_miss": 0.0, "miss": 6.0, "model": 63.0, "overflow": 6.0, "padding": 48.0, "tokens": 45258.0 }, { "bucket": 1120.0, "duration_ms": 7300.928393, "eligible_miss": 1.0, "miss": 2.0, "model": 72.0, "overflow": 1.0, "padding": 56.0, "tokens": 7547.0 }, { "bucket": 272.0, "duration_ms": 11811.300586999998, "eligible_miss": 0.0, "miss": 6.0, "model": 23.0, "overflow": 6.0, "padding": 35.0, "tokens": 47753.0 }, { "duration_ms": 11055.91304, "eligible_miss": 0.0, "miss": 5.0, "model": 5.0, "overflow": 5.0, "tokens": 40960.0 }, { "duration_ms": 8944.076589, "eligible_miss": 0.0, "miss": 5.0, "model": 5.0, "overflow": 5.0, "tokens": 39604.0 }, { "bucket": 80.0, "duration_ms": 9594.855515000001, "eligible_miss": 0.0, "miss": 6.0, "model": 11.0, "overflow": 6.0, "padding": 16.0, "tokens": 47376.0 }, { "bucket": 24.0, "duration_ms": 9620.566718, "eligible_miss": 0.0, "miss": 7.0, "model": 8.0, "overflow": 7.0, "padding": 7.0, "tokens": 54810.0 }, { "bucket": 1512.0, "duration_ms": 9199.070156999998, "eligible_miss": 1.0, "miss": 3.0, "model": 66.0, "overflow": 2.0, "padding": 296.0, "tokens": 11630.0 }, { "bucket": 432.0, "duration_ms": 10189.773732, "eligible_miss": 0.0, "miss": 6.0, "model": 24.0, "overflow": 6.0, "padding": 37.0, "tokens": 47726.0 }, { "bucket": 1576.0, "duration_ms": 9587.827011, "eligible_miss": 0.0, "miss": 4.0, "model": 64.0, "overflow": 4.0, "padding": 163.0, "tokens": 30393.0 }, { "bucket": 1608.0, "duration_ms": 9988.892738000002, "eligible_miss": 0.0, "miss": 5.0, "model": 63.0, "overflow": 5.0, "padding": 210.0, "tokens": 36002.0 }, { "bucket": 384.0, "duration_ms": 11564.252193, "eligible_miss": 0.0, "miss": 8.0, "model": 20.0, "overflow": 8.0, "padding": 71.0, "tokens": 64411.0 }, { "bucket": 192.0, "duration_ms": 10965.250629999999, "eligible_miss": 0.0, "miss": 6.0, "model": 12.0, "overflow": 6.0, "padding": 19.0, "tokens": 41855.0 }, { "duration_ms": 9069.412812, "eligible_miss": 0.0, "miss": 6.0, "model": 6.0, "overflow": 6.0, "tokens": 49152.0 }, { "bucket": 1376.0, "duration_ms": 8453.388135000001, "eligible_miss": 0.0, "miss": 3.0, "model": 46.0, "overflow": 3.0, "padding": 77.0, "tokens": 23205.0 } ], "clean": { "admitted": 196, "completed": 196, "completed_throughput_rps": 0.8166666666666667, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 1899551, "offered_rps": 0.8166666666666667, "output_tokens": 44004, "start_s": 60.0 }, "config": "C10", "drain_quarantined": false, "drain_seconds": 256.107847391977, "latency_s": { "e2e": { "mean": 144.9189226589494, "n": 196, "p50": 117.59595297249325, "p95": 282.36017964924395, "p99": 292.70826233768895 }, "tpot": { "mean": 0.1367971753786876, "n": 196, "p50": 0.1362825763050598, "p95": 0.18970892391759359, "p99": 0.26770929005363897 }, "ttft": { "mean": 114.34430171160724, "n": 196, "p50": 83.6976999160106, "p95": 257.0734725165021, "p99": 268.6144477106413 } }, "layer1": { "decode_tokens": 53087, "kv_usage_max": 1.0, "kv_usage_mean": 0.9697357124350795, "mode_counts": { "FULL": 1334, "NONE": 259 }, "mode_shares": { "FULL": 0.837413684871312, "NONE": 0.162586315128688 }, "preemptions": 16, "prefill_tokens": 1864054, "prefix_query_hit_ratio": 0.004917128512585017, "queue_waiting_max": 243, "queue_waiting_mean": 226.5593220338983, "records_all": 4180, "records_clean": 1593, "requests_per_step": { "mean": 29.18706842435656, "n": 1593, "p50": 19.0, "p95": 58.0, "p99": 61.0 }, "scheduled_tokens_per_step": { "mean": 1203.4783427495292, "n": 1593, "p50": 24.0, "p95": 8192.0, "p99": 8192.0 }, "step_duration_ms": { "mean": 301.2044153904583, "n": 1593, "p50": 79.154278, "p95": 1583.7362489999996, "p99": 2282.78115692 }, "token_efficiency_per_ms": 3.9955534555807635 }, "layer2_missing_after_controller_cleanup": false, "load": "saturation", "pattern": "P10", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 0.55, "clean_c_waiting_median": 237.0, "completion_rate_rps": 0.8, "completion_rate_within_10pct": false, "tail_end_s": 343.2937143140007, "tail_start_s": 333.2937143140007, "valid": false, "waiting_median": 216.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 0.55, "clean_c_waiting_median": 237.0, "completion_rate_rps": 0.3, "completion_rate_within_10pct": false, "tail_end_s": 376.3072694450093, "tail_start_s": 366.3072694450093, "valid": false, "waiting_median": 228.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 196, "run_dir": "runs/phase3/primary/P10-C10/saturation", "run_id": "P10-C10-saturation", "trace_files": 2, "waste": { "R128": 0.7047173851989379, "R32": 0.6764453342592629, "R64": 0.6923054365307624, "bucket_slack": 0.10055066079295154, "eligible_miss_rate": 0.003138731952291274, "graph_miss_rate": 0.162586315128688, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.15944758317639673, "padded_tokens_per_useful_token": 0.0023681095965294155, "padding_fraction": 0.10314431115957834 } }, "P10-C11-moderate": { "blocks": [ { "bucket": 503.0, "duration_ms": 8991.754106999995, "eligible_miss": 0.0, "miss": 14.0, "model": 510.0, "overflow": 14.0, "padding": 0.0, "tokens": 27059.0 }, { "duration_ms": 9836.927439, "eligible_miss": 0.0, "miss": 20.0, "model": 20.0, "overflow": 20.0, "tokens": 40960.0 }, { "bucket": 120.0, "duration_ms": 9811.257092, "eligible_miss": 0.0, "miss": 20.0, "model": 35.0, "overflow": 20.0, "padding": 44.0, "tokens": 39413.0 }, { "bucket": 1152.0, "duration_ms": 9848.213607, "eligible_miss": 0.0, "miss": 13.0, "model": 157.0, "overflow": 13.0, "padding": 283.0, "tokens": 26731.0 }, { "bucket": 424.0, "duration_ms": 10637.645715999999, "eligible_miss": 0.0, "miss": 20.0, "model": 73.0, "overflow": 20.0, "padding": 57.0, "tokens": 39993.0 }, { "bucket": 1512.0, "duration_ms": 9332.632807999998, "eligible_miss": 1.0, "miss": 8.0, "model": 225.0, "overflow": 7.0, "padding": 375.0, "tokens": 13027.0 }, { "bucket": 611.0, "duration_ms": 6026.108009999988, "eligible_miss": 1.0, "miss": 4.0, "model": 575.0, "overflow": 3.0, "padding": 10.0, "tokens": 6608.0 }, { "duration_ms": 9745.453402, "eligible_miss": 0.0, "miss": 17.0, "model": 17.0, "overflow": 17.0, "tokens": 34816.0 }, { "bucket": 228.0, "duration_ms": 9988.957895999996, "eligible_miss": 0.0, "miss": 21.0, "model": 78.0, "overflow": 21.0, "padding": 0.0, "tokens": 42459.0 }, { "bucket": 904.0, "duration_ms": 10263.974203999996, "eligible_miss": 1.0, "miss": 15.0, "model": 128.0, "overflow": 14.0, "padding": 226.0, "tokens": 29075.0 }, { "bucket": 528.0, "duration_ms": 9166.581995999995, "eligible_miss": 2.0, "miss": 16.0, "model": 72.0, "overflow": 14.0, "padding": 94.0, "tokens": 29752.0 }, { "bucket": 1842.0, "duration_ms": 8078.520900999999, "eligible_miss": 1.0, "miss": 3.0, "model": 437.0, "overflow": 2.0, "padding": 470.0, "tokens": 4395.0 }, { "bucket": 326.0, "duration_ms": 8712.581120999988, "eligible_miss": 0.0, "miss": 16.0, "model": 270.0, "overflow": 16.0, "padding": 0.0, "tokens": 31124.0 }, { "bucket": 543.0, "duration_ms": 9440.142476, "eligible_miss": 1.0, "miss": 14.0, "model": 308.0, "overflow": 13.0, "padding": 0.0, "tokens": 26918.0 }, { "bucket": 510.0, "duration_ms": 5693.341847, "eligible_miss": 0.0, "miss": 6.0, "model": 516.0, "overflow": 6.0, "padding": 0.0, "tokens": 11086.0 }, { "bucket": 755.0, "duration_ms": 9750.186765999988, "eligible_miss": 0.0, "miss": 13.0, "model": 357.0, "overflow": 13.0, "padding": 49.0, "tokens": 25127.0 }, { "bucket": 628.0, "duration_ms": 5739.3034739999985, "eligible_miss": 1.0, "miss": 5.0, "model": 466.0, "overflow": 4.0, "padding": 3.0, "tokens": 9184.0 }, { "bucket": 316.0, "duration_ms": 6905.508828000001, "eligible_miss": 0.0, "miss": 13.0, "model": 329.0, "overflow": 13.0, "padding": 0.0, "tokens": 24457.0 }, { "bucket": 707.0, "duration_ms": 8045.125614000001, "eligible_miss": 1.0, "miss": 7.0, "model": 516.0, "overflow": 6.0, "padding": 0.0, "tokens": 12122.0 }, { "bucket": 307.0, "duration_ms": 9190.669360999995, "eligible_miss": 1.0, "miss": 16.0, "model": 147.0, "overflow": 15.0, "padding": 36.0, "tokens": 31224.0 }, { "bucket": 644.0, "duration_ms": 4659.236079000004, "eligible_miss": 1.0, "miss": 2.0, "model": 452.0, "overflow": 1.0, "padding": 22.0, "tokens": 2032.0 }, { "bucket": 374.0, "duration_ms": 3697.778438000003, "eligible_miss": 0.0, "miss": 3.0, "model": 354.0, "overflow": 3.0, "padding": 5.0, "tokens": 5989.0 }, { "bucket": 590.0, "duration_ms": 8927.317469999984, "eligible_miss": 1.0, "miss": 11.0, "model": 575.0, "overflow": 10.0, "padding": 0.0, "tokens": 19420.0 }, { "bucket": 256.0, "duration_ms": 7494.414503999998, "eligible_miss": 1.0, "miss": 14.0, "model": 270.0, "overflow": 13.0, "padding": 0.0, "tokens": 26433.0 }, { "bucket": 749.0, "duration_ms": 10068.411879000008, "eligible_miss": 0.0, "miss": 17.0, "model": 263.0, "overflow": 17.0, "padding": 147.0, "tokens": 33581.0 }, { "bucket": 739.0, "duration_ms": 8692.409100999997, "eligible_miss": 0.0, "miss": 9.0, "model": 541.0, "overflow": 9.0, "padding": 37.0, "tokens": 18533.0 }, { "bucket": 722.0, "duration_ms": 8879.877492, "eligible_miss": 0.0, "miss": 10.0, "model": 529.0, "overflow": 10.0, "padding": 3.0, "tokens": 20752.0 }, { "bucket": 650.0, "duration_ms": 8948.98821000001, "eligible_miss": 1.0, "miss": 10.0, "model": 636.0, "overflow": 9.0, "padding": 0.0, "tokens": 16903.0 }, { "bucket": 367.0, "duration_ms": 7598.144262000002, "eligible_miss": 0.0, "miss": 11.0, "model": 378.0, "overflow": 11.0, "padding": 0.0, "tokens": 21755.0 }, { "bucket": 484.0, "duration_ms": 9681.970063000002, "eligible_miss": 0.0, "miss": 17.0, "model": 138.0, "overflow": 17.0, "padding": 121.0, "tokens": 33652.0 }, { "bucket": 952.0, "duration_ms": 9716.605327000007, "eligible_miss": 0.0, "miss": 13.0, "model": 196.0, "overflow": 13.0, "padding": 201.0, "tokens": 25588.0 }, { "bucket": 869.0, "duration_ms": 6559.674515999999, "eligible_miss": 0.0, "miss": 5.0, "model": 473.0, "overflow": 5.0, "padding": 128.0, "tokens": 10417.0 }, { "bucket": 495.0, "duration_ms": 7574.075480000001, "eligible_miss": 0.0, "miss": 9.0, "model": 504.0, "overflow": 9.0, "padding": 0.0, "tokens": 18569.0 }, { "bucket": 597.0, "duration_ms": 8411.306683000006, "eligible_miss": 0.0, "miss": 6.0, "model": 432.0, "overflow": 6.0, "padding": 0.0, "tokens": 11847.0 }, { "bucket": 345.0, "duration_ms": 5015.054257000001, "eligible_miss": 1.0, "miss": 8.0, "model": 353.0, "overflow": 7.0, "padding": 0.0, "tokens": 13607.0 }, { "bucket": 538.0, "duration_ms": 9609.595639999996, "eligible_miss": 1.0, "miss": 16.0, "model": 251.0, "overflow": 15.0, "padding": 87.0, "tokens": 29841.0 }, { "bucket": 832.0, "duration_ms": 6853.801568000002, "eligible_miss": 2.0, "miss": 5.0, "model": 528.0, "overflow": 3.0, "padding": 70.0, "tokens": 7678.0 }, { "bucket": 648.0, "duration_ms": 7249.697015, "eligible_miss": 1.0, "miss": 6.0, "model": 654.0, "overflow": 5.0, "padding": 0.0, "tokens": 10122.0 }, { "bucket": 352.0, "duration_ms": 9321.284261999997, "eligible_miss": 0.0, "miss": 16.0, "model": 289.0, "overflow": 16.0, "padding": 7.0, "tokens": 33113.0 }, { "bucket": 1092.0, "duration_ms": 8666.118680999994, "eligible_miss": 0.0, "miss": 4.0, "model": 556.0, "overflow": 4.0, "padding": 143.0, "tokens": 6943.0 }, { "bucket": 491.0, "duration_ms": 8220.941466999995, "eligible_miss": 0.0, "miss": 11.0, "model": 453.0, "overflow": 11.0, "padding": 0.0, "tokens": 22531.0 }, { "bucket": 821.0, "duration_ms": 9977.426195000007, "eligible_miss": 0.0, "miss": 11.0, "model": 358.0, "overflow": 11.0, "padding": 61.0, "tokens": 23256.0 }, { "bucket": 511.0, "duration_ms": 4679.773215999997, "eligible_miss": 0.0, "miss": 2.0, "model": 513.0, "overflow": 2.0, "padding": 0.0, "tokens": 2680.0 }, { "bucket": 344.0, "duration_ms": 5247.637218999998, "eligible_miss": 2.0, "miss": 9.0, "model": 353.0, "overflow": 7.0, "padding": 0.0, "tokens": 14579.0 }, { "bucket": 665.0, "duration_ms": 8615.953720000001, "eligible_miss": 0.0, "miss": 8.0, "model": 617.0, "overflow": 8.0, "padding": 0.0, "tokens": 16312.0 }, { "bucket": 239.0, "duration_ms": 9411.176352999995, "eligible_miss": 1.0, "miss": 18.0, "model": 257.0, "overflow": 17.0, "padding": 0.0, "tokens": 35195.0 }, { "bucket": 508.0, "duration_ms": 9621.412921, "eligible_miss": 0.0, "miss": 13.0, "model": 140.0, "overflow": 13.0, "padding": 31.0, "tokens": 26633.0 }, { "bucket": 116.0, "duration_ms": 11128.783442000002, "eligible_miss": 1.0, "miss": 19.0, "model": 48.0, "overflow": 18.0, "padding": 0.0, "tokens": 37285.0 } ], "clean": { "admitted": 116, "completed": 111, "completed_throughput_rps": 0.4625, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 968714, "offered_rps": 0.48333333333333334, "output_tokens": 25409, "start_s": 60.0 }, "config": "C11", "drain_quarantined": false, "drain_seconds": 2.1805057660094462, "latency_s": { "e2e": { "mean": 4.364980708677919, "n": 111, "p50": 2.5644153020111844, "p95": 15.528192899510032, "p99": 17.251885565518755 }, "tpot": { "mean": 0.013476979717565554, "n": 111, "p50": 0.007207736172530727, "p95": 0.048615745335301455, "p99": 0.05342051563131643 }, "ttft": { "mean": 1.111188190306174, "n": 111, "p50": 0.7105740209808573, "p95": 3.396348365509766, "p99": 4.767139900015901 } }, "layer1": { "decode_tokens": 25661, "kv_usage_max": 0.39101211794142177, "kv_usage_mean": 0.04664282350048209, "mode_counts": { "FULL": 15795, "NONE": 640, "PIECEWISE": 8 }, "mode_shares": { "FULL": 0.9605911330049262, "NONE": 0.038922337772912485, "PIECEWISE": 0.00048652922216140606 }, "preemptions": 0, "prefill_tokens": 1025115, "prefix_query_hit_ratio": 0.0167845310754508, "queue_waiting_max": 1, "queue_waiting_mean": 0.0024326461108070303, "records_all": 22073, "records_clean": 16443, "requests_per_step": { "mean": 1.59514687100894, "n": 16443, "p50": 1.0, "p95": 5.0, "p99": 7.0 }, "scheduled_tokens_per_step": { "mean": 63.904153743234204, "n": 16443, "p50": 1.0, "p95": 6.0, "p99": 2048.0 }, "step_duration_ms": { "mean": 24.31026893662957, "n": 16443, "p50": 9.632865, "p95": 31.7124496, "p99": 461.83891844 }, "token_efficiency_per_ms": 2.6286897076217217 }, "layer2_missing_after_controller_cleanup": false, "load": "moderate", "pattern": "P10", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 0.5, "clean_c_waiting_median": 0.0, "completion_rate_rps": 0.1, "completion_rate_within_10pct": false, "tail_end_s": 345.9574947899964, "tail_start_s": 335.9574947899964, "valid": false, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 0.5, "clean_c_waiting_median": 0.0, "completion_rate_rps": 0.3, "completion_rate_within_10pct": false, "tail_end_s": 379.9735003169917, "tail_start_s": 369.9735003169917, "valid": false, "waiting_median": 0.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 111, "run_dir": "runs/phase3/primary/P10-C11/moderate", "run_id": "P10-C11-moderate", "trace_files": 2, "waste": { "R128": 0.7047173851989379, "R32": 0.6764453342592629, "R64": 0.6923054365307624, "bucket_slack": 0.0805340710212838, "eligible_miss_rate": 0.0014069859913133909, "graph_miss_rate": 0.0332782773597602, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.03187129136844681, "padded_tokens_per_useful_token": 0.002579046342893252, "padding_fraction": 0.09711173224396187 } }, "P10-C11-saturation": { "blocks": [ { "duration_ms": 9803.640058999998, "eligible_miss": 0.0, "miss": 26.0, "model": 26.0, "overflow": 26.0, "tokens": 53248.0 }, { "bucket": 5880.0, "duration_ms": 9835.950327000006, "eligible_miss": 1.0, "miss": 7.0, "model": 100.0, "overflow": 6.0, "padding": 462.0, "tokens": 15976.0 }, { "bucket": 392.0, "duration_ms": 10336.127500000002, "eligible_miss": 0.0, "miss": 26.0, "model": 33.0, "overflow": 26.0, "padding": 1.0, "tokens": 53639.0 }, { "duration_ms": 9842.753817000003, "eligible_miss": 0.0, "miss": 27.0, "model": 27.0, "overflow": 27.0, "tokens": 55296.0 }, { "duration_ms": 10500.215170000001, "eligible_miss": 0.0, "miss": 26.0, "model": 26.0, "overflow": 26.0, "tokens": 53248.0 }, { "duration_ms": 9819.693657000002, "eligible_miss": 0.0, "miss": 25.0, "model": 25.0, "overflow": 25.0, "tokens": 51200.0 }, { "duration_ms": 9582.212909000002, "eligible_miss": 0.0, "miss": 23.0, "model": 23.0, "overflow": 23.0, "tokens": 47104.0 }, { "bucket": 112.0, "duration_ms": 10275.247018, "eligible_miss": 0.0, "miss": 25.0, "model": 27.0, "overflow": 25.0, "padding": 1.0, "tokens": 50799.0 }, { "bucket": 2760.0, "duration_ms": 9618.081895000001, "eligible_miss": 2.0, "miss": 17.0, "model": 62.0, "overflow": 15.0, "padding": 177.0, "tokens": 31342.0 }, { "bucket": 2912.0, "duration_ms": 11031.054516, "eligible_miss": 1.0, "miss": 13.0, "model": 66.0, "overflow": 12.0, "padding": 239.0, "tokens": 27706.0 }, { "duration_ms": 9609.575980999998, "eligible_miss": 0.0, "miss": 16.0, "model": 16.0, "overflow": 16.0, "tokens": 31606.0 }, { "duration_ms": 9580.234407, "eligible_miss": 0.0, "miss": 17.0, "model": 17.0, "overflow": 17.0, "tokens": 34816.0 }, { "bucket": 40.0, "duration_ms": 10043.451591, "eligible_miss": 0.0, "miss": 20.0, "model": 21.0, "overflow": 20.0, "padding": 4.0, "tokens": 39801.0 }, { "duration_ms": 10257.613201999999, "eligible_miss": 0.0, "miss": 19.0, "model": 19.0, "overflow": 19.0, "tokens": 38912.0 }, { "duration_ms": 9893.364799, "eligible_miss": 0.0, "miss": 19.0, "model": 19.0, "overflow": 19.0, "tokens": 38912.0 }, { "duration_ms": 9812.629688, "eligible_miss": 0.0, "miss": 20.0, "model": 20.0, "overflow": 20.0, "tokens": 40960.0 }, { "duration_ms": 10162.704605, "eligible_miss": 0.0, "miss": 18.0, "model": 18.0, "overflow": 18.0, "tokens": 36864.0 }, { "duration_ms": 10096.544445, "eligible_miss": 0.0, "miss": 21.0, "model": 21.0, "overflow": 21.0, "tokens": 43008.0 }, { "bucket": 192.0, "duration_ms": 9439.287972999999, "eligible_miss": 0.0, "miss": 15.0, "model": 21.0, "overflow": 15.0, "padding": 38.0, "tokens": 30874.0 }, { "bucket": 1440.0, "duration_ms": 10398.481440000001, "eligible_miss": 0.0, "miss": 9.0, "model": 96.0, "overflow": 9.0, "padding": 43.0, "tokens": 19829.0 }, { "bucket": 64.0, "duration_ms": 10069.123950999998, "eligible_miss": 0.0, "miss": 21.0, "model": 24.0, "overflow": 21.0, "padding": 14.0, "tokens": 42743.0 }, { "duration_ms": 10163.353964999998, "eligible_miss": 0.0, "miss": 22.0, "model": 22.0, "overflow": 22.0, "tokens": 45056.0 }, { "duration_ms": 9601.490734, "eligible_miss": 0.0, "miss": 19.0, "model": 19.0, "overflow": 19.0, "tokens": 38912.0 }, { "duration_ms": 9938.422147000001, "eligible_miss": 0.0, "miss": 20.0, "model": 20.0, "overflow": 20.0, "tokens": 40389.0 }, { "bucket": 72.0, "duration_ms": 10031.912896999998, "eligible_miss": 0.0, "miss": 23.0, "model": 25.0, "overflow": 23.0, "padding": 6.0, "tokens": 47170.0 }, { "bucket": 240.0, "duration_ms": 9938.585003, "eligible_miss": 0.0, "miss": 18.0, "model": 28.0, "overflow": 18.0, "padding": 52.0, "tokens": 35610.0 }, { "bucket": 96.0, "duration_ms": 10070.516326, "eligible_miss": 0.0, "miss": 22.0, "model": 26.0, "overflow": 22.0, "padding": 21.0, "tokens": 44167.0 }, { "bucket": 1248.0, "duration_ms": 9806.104926000007, "eligible_miss": 0.0, "miss": 12.0, "model": 64.0, "overflow": 12.0, "padding": 209.0, "tokens": 23747.0 }, { "bucket": 648.0, "duration_ms": 10603.34154, "eligible_miss": 0.0, "miss": 18.0, "model": 45.0, "overflow": 18.0, "padding": 111.0, "tokens": 37401.0 }, { "duration_ms": 9530.284238, "eligible_miss": 0.0, "miss": 20.0, "model": 20.0, "overflow": 20.0, "tokens": 40960.0 }, { "duration_ms": 10103.438895999998, "eligible_miss": 0.0, "miss": 20.0, "model": 20.0, "overflow": 20.0, "tokens": 40960.0 }, { "duration_ms": 10733.006420000002, "eligible_miss": 1.0, "miss": 21.0, "model": 21.0, "overflow": 20.0, "tokens": 41432.0 }, { "duration_ms": 9224.846354000001, "eligible_miss": 0.0, "miss": 16.0, "model": 16.0, "overflow": 16.0, "tokens": 32516.0 }, { "duration_ms": 10388.344382, "eligible_miss": 0.0, "miss": 19.0, "model": 19.0, "overflow": 19.0, "tokens": 37733.0 }, { "bucket": 544.0, "duration_ms": 10253.314467000004, "eligible_miss": 0.0, "miss": 14.0, "model": 39.0, "overflow": 14.0, "padding": 88.0, "tokens": 29128.0 }, { "bucket": 32.0, "duration_ms": 9439.055381000002, "eligible_miss": 0.0, "miss": 14.0, "model": 16.0, "overflow": 14.0, "padding": 3.0, "tokens": 28677.0 }, { "duration_ms": 10483.385640999999, "eligible_miss": 0.0, "miss": 17.0, "model": 17.0, "overflow": 17.0, "tokens": 33881.0 }, { "bucket": 944.0, "duration_ms": 10235.9488, "eligible_miss": 0.0, "miss": 11.0, "model": 70.0, "overflow": 11.0, "padding": 114.0, "tokens": 23358.0 }, { "bucket": 144.0, "duration_ms": 9260.176585000001, "eligible_miss": 0.0, "miss": 18.0, "model": 27.0, "overflow": 18.0, "padding": 20.0, "tokens": 35688.0 }, { "bucket": 208.0, "duration_ms": 10099.584046999998, "eligible_miss": 0.0, "miss": 16.0, "model": 24.0, "overflow": 16.0, "padding": 22.0, "tokens": 32954.0 }, { "bucket": 240.0, "duration_ms": 9581.310761, "eligible_miss": 0.0, "miss": 16.0, "model": 31.0, "overflow": 16.0, "padding": 46.0, "tokens": 32833.0 }, { "duration_ms": 10818.639540999997, "eligible_miss": 0.0, "miss": 20.0, "model": 20.0, "overflow": 20.0, "tokens": 40960.0 }, { "duration_ms": 9592.901207, "eligible_miss": 0.0, "miss": 15.0, "model": 15.0, "overflow": 15.0, "tokens": 30720.0 }, { "bucket": 496.0, "duration_ms": 10098.093245999999, "eligible_miss": 0.0, "miss": 16.0, "model": 47.0, "overflow": 16.0, "padding": 94.0, "tokens": 32618.0 }, { "duration_ms": 9722.888504, "eligible_miss": 0.0, "miss": 16.0, "model": 16.0, "overflow": 16.0, "tokens": 32768.0 }, { "duration_ms": 10337.847011, "eligible_miss": 0.0, "miss": 17.0, "model": 17.0, "overflow": 17.0, "tokens": 34816.0 }, { "bucket": 880.0, "duration_ms": 9603.342421999998, "eligible_miss": 0.0, "miss": 8.0, "model": 63.0, "overflow": 8.0, "padding": 166.0, "tokens": 16514.0 }, { "bucket": 16.0, "duration_ms": 10377.703795, "eligible_miss": 1.0, "miss": 17.0, "model": 18.0, "overflow": 16.0, "padding": 4.0, "tokens": 33158.0 } ], "clean": { "admitted": 193, "completed": 193, "completed_throughput_rps": 0.8041666666666667, "duration_s": 240.0, "end_s": 300.0, "failed": 0, "input_tokens": 1762708, "offered_rps": 0.8041666666666667, "output_tokens": 44197, "start_s": 60.0 }, "config": "C11", "drain_quarantined": false, "drain_seconds": 273.14732490401366, "latency_s": { "e2e": { "mean": 134.18431260923774, "n": 193, "p50": 111.3837862299988, "p95": 258.4493683842126, "p99": 287.67599090651015 }, "tpot": { "mean": 0.15051965069877637, "n": 193, "p50": 0.1509121470940847, "p95": 0.1897459957210793, "p99": 0.2325328770395698 }, "ttft": { "mean": 100.05380060465345, "n": 193, "p50": 83.08665158701479, "p95": 216.04882907219576, "p99": 245.99976527046636 } }, "layer1": { "decode_tokens": 42219, "kv_usage_max": 0.9999509395084138, "kv_usage_mean": 0.9401752966026676, "mode_counts": { "FULL": 592, "NONE": 875, "PIECEWISE": 5 }, "mode_shares": { "FULL": 0.40217391304347827, "NONE": 0.5944293478260869, "PIECEWISE": 0.0033967391304347825 }, "preemptions": 3, "prefill_tokens": 1739790, "prefix_query_hit_ratio": 0.004341961412847301, "queue_waiting_max": 244, "queue_waiting_mean": 227.1576086956522, "records_all": 4155, "records_clean": 1472, "requests_per_step": { "mean": 28.575407608695652, "n": 1472, "p50": 19.0, "p95": 59.0, "p99": 62.0 }, "scheduled_tokens_per_step": { "mean": 1210.6039402173913, "n": 1472, "p50": 2048.0, "p95": 2048.0, "p99": 2048.0 }, "step_duration_ms": { "mean": 326.1180898002717, "n": 1472, "p50": 347.0396935, "p95": 729.4108498, "p99": 859.3618077799999 }, "token_efficiency_per_ms": 3.7121643296721607 }, "layer2_missing_after_controller_cleanup": false, "load": "saturation", "pattern": "P10", "profile_recovery": [ { "clean_c_completion_rate_median_rps": 0.3, "clean_c_waiting_median": 243.0, "completion_rate_rps": 0.4, "completion_rate_within_10pct": false, "tail_end_s": 349.9593778490089, "tail_start_s": 339.9593778490089, "valid": false, "waiting_median": 227.0, "waiting_within_10pct": true, "window": 1 }, { "clean_c_completion_rate_median_rps": 0.3, "clean_c_waiting_median": 243.0, "completion_rate_rps": 0.9, "completion_rate_within_10pct": false, "tail_end_s": 383.3783031209896, "tail_start_s": 373.3783031209896, "valid": false, "waiting_median": 219.0, "waiting_within_10pct": true, "window": 2 } ], "profile_recovery_valid": false, "requests_completed": 193, "run_dir": "runs/phase3/primary/P10-C11/saturation", "run_id": "P10-C11-saturation", "trace_files": 2, "waste": { "R128": 0.7047173851989379, "R32": 0.6764453342592629, "R64": 0.6923054365307624, "bucket_slack": 0.08936285097192224, "eligible_miss_rate": 0.004076086956521739, "graph_miss_rate": 0.5944293478260869, "mixed_interference": null, "moe_layer_cv": null, "overflow_rate": 0.5903532608695652, "padded_tokens_per_useful_token": 0.0010858531017520115, "padding_fraction": 0.09872448979591837 } } }, "sanity": { "declared_deviations": { "invalid_primary_layer2_windows": [ "P01-C00-moderate: window 1", "P01-C00-moderate: window 2", "P02-C00-moderate: window 1", "P02-C00-moderate: window 2", "P03-C00-moderate: window 1", "P03-C00-moderate: window 2", "P06-C00-moderate: window 1", "P06-C00-moderate: window 2", "P07-C00-moderate: window 1", "P07-C00-moderate: window 2", "P08-C00-moderate: window 1", "P08-C00-moderate: window 2", "P09-C00-moderate: window 1", "P09-C00-moderate: window 2", "P10-C00-moderate: window 1", "P10-C00-moderate: window 2" ], "missing_cells": [ "P03/C11", "P05/C00", "P10/C00-TP2", "P11/C00" ], "missing_confirmations": [ "P10", "P06", "P03", "P01" ], "missing_saturation_traces": 8, "moe_layer_cv": "N/A: layer scopes do not cover >=80% of MoE GEMM time", "unaccepted_canonical_run_markers_excluded": [ "P11-C00-saturation" ] }, "invariants": { "accepted_run_ids_unique": true, "ap36_operational_finding_reproduced": true, "ap37_confirmation_runs_0": true, "ap37_primary_runs_40": true, "clean_duration_240": true, "clean_failures_zero": true, "clock_and_load_snapshots_complete": true, "complete_cells_20": true, "complete_stage_count_12": true, "completed_c00_patterns_9": true, "controller_frozen_at_ap36_failure": true, "drain_quarantine_under_20pct": true, "h1b_evaluable_contrasts_6": true, "h1b_missing_contrasts_exact": true, "layer1_footer_invariants": true, "missing_cells_exact": true, "missing_trace_count_accepted_8": true, "moderate_rate_within_5pct": true, "no_layer2_parser_issues": true, "other_gpu_processes_absent": true, "patterns_not_all_identical_throughput": true, "ratios_in_unit_interval": true, "trace_count_accepted_72": true }, "numeric": { "completed_throughput_rps": { "distinct_n": 37, "finite_n": 40, "max": 43.3, "min": 0.44583333333333336, "missing_n": 0, "n": 40 }, "drain_seconds": { "distinct_n": 40, "finite_n": 40, "max": 288.6191079240234, "min": 0.3054194079886656, "missing_n": 0, "n": 40 }, "kendall_tau_b": { "distinct_n": 0, "finite_n": 0, "max": null, "min": null, "missing_n": 0, "n": 0 }, "layer1_clean_steps": { "distinct_n": 40, "finite_n": 40, "max": 20171.0, "min": 718.0, "missing_n": 0, "n": 40 }, "operator_classifiable_fraction": { "distinct_n": 72, "finite_n": 72, "max": 0.9963781377235988, "min": 0.9704584620048622, "missing_n": 0, "n": 72 }, "operator_share": { "distinct_n": 348, "finite_n": 576, "max": 0.8734165832313857, "min": 0.0, "missing_n": 0, "n": 576 }, "token_efficiency_per_ms": { "distinct_n": 40, "finite_n": 40, "max": 8.29584869763246, "min": 2.147827352932598, "missing_n": 0, "n": 40 }, "waste_contrast_effect": { "distinct_n": 17, "finite_n": 24, "max": 0.5204129156598252, "min": -0.20308199280724987, "missing_n": 12, "n": 36 }, "waste_ratios": { "distinct_n": 168, "finite_n": 240, "max": 1.0, "min": 0.0, "missing_n": 0, "n": 240 } } }, "schema": 1, "waste_contrast_status": [ { "control": "P01", "efficiency_loss": null, "evaluable": false, "irregular": "P05", "metrics": [], "missing_cells": [ "P05-C00" ], "passes_h1b": false, "passing_metrics": [], "verdict": "NOT_EVALUABLE" }, { "control": "P03", "efficiency_loss": null, "evaluable": false, "irregular": "P05", "metrics": [], "missing_cells": [ "P05-C00" ], "passes_h1b": false, "passing_metrics": [], "verdict": "NOT_EVALUABLE" }, { "control": "P02", "efficiency_loss": 0.11608997226921058, "evaluable": true, "irregular": "P06", "metrics": [ { "available": true, "ci95_high": -0.01613620902704422, "ci95_low": -0.018335446670663714, "coincident_efficiency_or_residual": true, "control": "P02", "efficiency_loss": 0.11608997226921058, "evaluable": true, "irregular": "P06", "material": false, "metric": "padding_fraction", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": -0.017218083890213506, "simultaneous_high": -0.0157356399373619, "simultaneous_low": -0.0187887535849442 }, { "available": true, "ci95_high": -0.026647777870177056, "ci95_low": -0.03356127646776247, "coincident_efficiency_or_residual": true, "control": "P02", "efficiency_loss": 0.11608997226921058, "evaluable": true, "irregular": "P06", "material": false, "metric": "graph_miss_rate", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": -0.03006598445684061, "simultaneous_high": -0.02530594241869426, "simultaneous_low": -0.03499903509242671 }, { "available": true, "ci95_high": -0.026633809539104453, "ci95_low": -0.033569133608294076, "coincident_efficiency_or_residual": true, "control": "P02", "efficiency_loss": 0.11608997226921058, "evaluable": true, "irregular": "P06", "material": false, "metric": "overflow_rate", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": -0.03006598445684061, "simultaneous_high": -0.025351137872591654, "simultaneous_low": -0.0349968653294319 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P02", "efficiency_loss": 0.11608997226921058, "evaluable": true, "irregular": "P06", "material": false, "metric": "mixed_interference", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null }, { "available": true, "ci95_high": 0.23494534783397408, "ci95_low": 0.2253590527218157, "coincident_efficiency_or_residual": true, "control": "P02", "efficiency_loss": 0.11608997226921058, "evaluable": true, "irregular": "P06", "material": true, "metric": "R64", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.2301483528866904, "simultaneous_high": 0.23683442206671917, "simultaneous_low": 0.22345003461028415 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P02", "efficiency_loss": 0.11608997226921058, "evaluable": true, "irregular": "P06", "material": false, "metric": "moe_layer_cv", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null } ], "missing_cells": [], "passes_h1b": true, "passing_metrics": [ "R64" ], "verdict": "PASS" }, { "control": "P04", "efficiency_loss": 0.2284629366493368, "evaluable": true, "irregular": "P06", "metrics": [ { "available": true, "ci95_high": 0.0018881170209094382, "ci95_low": 0.00013272036050889215, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.2284629366493368, "evaluable": true, "irregular": "P06", "material": false, "metric": "padding_fraction", "p": 0.02776, "p_holm": 0.08327999999999999, "passes_h1b": false, "point": 0.001092906862063869, "simultaneous_high": 0.002162520644872445, "simultaneous_low": -0.0002871891115189649 }, { "available": true, "ci95_high": -0.000493778899366458, "ci95_low": -0.010138790500287403, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.2284629366493368, "evaluable": true, "irregular": "P06", "material": false, "metric": "graph_miss_rate", "p": 0.02632, "p_holm": 0.10528, "passes_h1b": false, "point": -0.004704030248702935, "simultaneous_high": 0.0009672756203671407, "simultaneous_low": -0.012632664546359583 }, { "available": true, "ci95_high": -0.0005068842298477604, "ci95_low": -0.010089468512164912, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.2284629366493368, "evaluable": true, "irregular": "P06", "material": false, "metric": "overflow_rate", "p": 0.02672, "p_holm": 0.10688, "passes_h1b": false, "point": -0.004704030248702935, "simultaneous_high": 0.0009123995960551078, "simultaneous_low": -0.012541358318390415 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.2284629366493368, "evaluable": true, "irregular": "P06", "material": false, "metric": "mixed_interference", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null }, { "available": true, "ci95_high": 0.3588237662068493, "ci95_low": 0.34996301147907066, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.2284629366493368, "evaluable": true, "irregular": "P06", "material": true, "metric": "R64", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.3543970834375052, "simultaneous_high": 0.3605880124391376, "simultaneous_low": 0.34826154238421436 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.2284629366493368, "evaluable": true, "irregular": "P06", "material": false, "metric": "moe_layer_cv", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null } ], "missing_cells": [], "passes_h1b": true, "passing_metrics": [ "R64" ], "verdict": "PASS" }, { "control": "P01", "efficiency_loss": 0.08324816211784114, "evaluable": true, "irregular": "P09", "metrics": [ { "available": true, "ci95_high": 0.07258101928545771, "ci95_low": 0.06107199918894719, "coincident_efficiency_or_residual": true, "control": "P01", "efficiency_loss": 0.08324816211784114, "evaluable": true, "irregular": "P09", "material": true, "metric": "padding_fraction", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.0667290414201105, "simultaneous_high": 0.07492451384312424, "simultaneous_low": 0.058870086990988876 }, { "available": true, "ci95_high": -0.18669616533208697, "ci95_low": -0.21919298047891625, "coincident_efficiency_or_residual": true, "control": "P01", "efficiency_loss": 0.08324816211784114, "evaluable": true, "irregular": "P09", "material": false, "metric": "graph_miss_rate", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": -0.20308199280724987, "simultaneous_high": -0.18011971739412205, "simultaneous_low": -0.2256276809071987 }, { "available": true, "ci95_high": -0.18660802863031692, "ci95_low": -0.21934591413132573, "coincident_efficiency_or_residual": true, "control": "P01", "efficiency_loss": 0.08324816211784114, "evaluable": true, "irregular": "P09", "material": false, "metric": "overflow_rate", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": -0.20308199280724987, "simultaneous_high": -0.18035129413637946, "simultaneous_low": -0.22589311960316016 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P01", "efficiency_loss": 0.08324816211784114, "evaluable": true, "irregular": "P09", "material": false, "metric": "mixed_interference", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null }, { "available": true, "ci95_high": 0.4001054362524198, "ci95_low": 0.3922157126916775, "coincident_efficiency_or_residual": true, "control": "P01", "efficiency_loss": 0.08324816211784114, "evaluable": true, "irregular": "P09", "material": true, "metric": "R64", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.39616418510901036, "simultaneous_high": 0.4016625621683738, "simultaneous_low": 0.3906536566040832 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P01", "efficiency_loss": 0.08324816211784114, "evaluable": true, "irregular": "P09", "material": false, "metric": "moe_layer_cv", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null } ], "missing_cells": [], "passes_h1b": true, "passing_metrics": [ "padding_fraction", "R64" ], "verdict": "PASS" }, { "control": "P03", "efficiency_loss": 0.03840305601484284, "evaluable": true, "irregular": "P09", "metrics": [ { "available": true, "ci95_high": 0.09130100661903304, "ci95_low": 0.07976380555258109, "coincident_efficiency_or_residual": false, "control": "P03", "efficiency_loss": 0.03840305601484284, "evaluable": true, "irregular": "P09", "material": true, "metric": "padding_fraction", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": 0.08542101015535679, "simultaneous_high": 0.09354749622519089, "simultaneous_low": 0.0776469398212851 }, { "available": true, "ci95_high": 0.03477003572235889, "ci95_low": 0.022150480290407913, "coincident_efficiency_or_residual": false, "control": "P03", "efficiency_loss": 0.03840305601484284, "evaluable": true, "irregular": "P09", "material": false, "metric": "graph_miss_rate", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": 0.027825216312380757, "simultaneous_high": 0.0379073029527558, "simultaneous_low": 0.020262740610606924 }, { "available": true, "ci95_high": 0.03478537546264273, "ci95_low": 0.022157030355767448, "coincident_efficiency_or_residual": false, "control": "P03", "efficiency_loss": 0.03840305601484284, "evaluable": true, "irregular": "P09", "material": false, "metric": "overflow_rate", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": 0.027825216312380757, "simultaneous_high": 0.038155569680251286, "simultaneous_low": 0.020260913333777324 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": false, "control": "P03", "efficiency_loss": 0.03840305601484284, "evaluable": true, "irregular": "P09", "material": false, "metric": "mixed_interference", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null }, { "available": true, "ci95_high": 0.5238722090454428, "ci95_low": 0.5169233936643203, "coincident_efficiency_or_residual": false, "control": "P03", "efficiency_loss": 0.03840305601484284, "evaluable": true, "irregular": "P09", "material": true, "metric": "R64", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": 0.5204129156598252, "simultaneous_high": 0.5252564301232907, "simultaneous_low": 0.5155191519515977 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": false, "control": "P03", "efficiency_loss": 0.03840305601484284, "evaluable": true, "irregular": "P09", "material": false, "metric": "moe_layer_cv", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null } ], "missing_cells": [], "passes_h1b": false, "passing_metrics": [], "verdict": "NO_QUALIFYING_METRIC" }, { "control": "P03", "efficiency_loss": 0.4469310402722787, "evaluable": true, "irregular": "P10", "metrics": [ { "available": true, "ci95_high": 0.08855777444708128, "ci95_low": 0.027415277773332525, "coincident_efficiency_or_residual": true, "control": "P03", "efficiency_loss": 0.4469310402722787, "evaluable": true, "irregular": "P10", "material": true, "metric": "padding_fraction", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.05565211993295673, "simultaneous_high": 0.10341073102256013, "simultaneous_low": 0.020097017796153225 }, { "available": true, "ci95_high": -0.00601669947733407, "ci95_low": -0.009872845681590466, "coincident_efficiency_or_residual": true, "control": "P03", "efficiency_loss": 0.4469310402722787, "evaluable": true, "irregular": "P10", "material": false, "metric": "graph_miss_rate", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": -0.008145427700863333, "simultaneous_high": -0.0049986468588015505, "simultaneous_low": -0.010459290275607078 }, { "available": true, "ci95_high": -0.006012535696644192, "ci95_low": -0.00989506245698499, "coincident_efficiency_or_residual": true, "control": "P03", "efficiency_loss": 0.4469310402722787, "evaluable": true, "irregular": "P10", "material": false, "metric": "overflow_rate", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": -0.008145427700863333, "simultaneous_high": -0.005013934447667286, "simultaneous_low": -0.010471471437559795 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P03", "efficiency_loss": 0.4469310402722787, "evaluable": true, "irregular": "P10", "material": false, "metric": "mixed_interference", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null }, { "available": true, "ci95_high": 0.4561736305824604, "ci95_low": 0.43955479496868705, "coincident_efficiency_or_residual": true, "control": "P03", "efficiency_loss": 0.4469310402722787, "evaluable": true, "irregular": "P10", "material": true, "metric": "R64", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.4478716685574937, "simultaneous_high": 0.459713780733712, "simultaneous_low": 0.43635435003093426 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P03", "efficiency_loss": 0.4469310402722787, "evaluable": true, "irregular": "P10", "material": false, "metric": "moe_layer_cv", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null } ], "missing_cells": [], "passes_h1b": true, "passing_metrics": [ "padding_fraction", "R64" ], "verdict": "PASS" }, { "control": "P04", "efficiency_loss": 0.1425966128421564, "evaluable": true, "irregular": "P10", "metrics": [ { "available": true, "ci95_high": 0.08668052314167546, "ci95_low": 0.025823274229141942, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.1425966128421564, "evaluable": true, "irregular": "P10", "material": true, "metric": "padding_fraction", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.05398526806052646, "simultaneous_high": 0.10213016668480329, "simultaneous_low": 0.018683381445978635 }, { "available": true, "ci95_high": 0.0007610647800286464, "ci95_low": -0.00936641415445055, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.1425966128421564, "evaluable": true, "irregular": "P10", "material": false, "metric": "graph_miss_rate", "p": 0.10722, "p_holm": 0.32166, "passes_h1b": false, "point": -0.0037955725000514817, "simultaneous_high": 0.0023548687154005257, "simultaneous_low": -0.011962189207249601 }, { "available": true, "ci95_high": 0.0007651798910721392, "ci95_low": -0.009350365146339001, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.1425966128421564, "evaluable": true, "irregular": "P10", "material": false, "metric": "overflow_rate", "p": 0.10804, "p_holm": 0.32411999999999996, "passes_h1b": false, "point": -0.0037955725000514817, "simultaneous_high": 0.0023480385252717118, "simultaneous_low": -0.011930615598005356 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.1425966128421564, "evaluable": true, "irregular": "P10", "material": false, "metric": "mixed_interference", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null }, { "available": true, "ci95_high": 0.45618061702156487, "ci95_low": 0.4395710696329076, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.1425966128421564, "evaluable": true, "irregular": "P10", "material": true, "metric": "R64", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.4478716685574937, "simultaneous_high": 0.4594884290583298, "simultaneous_low": 0.4363807227134572 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.1425966128421564, "evaluable": true, "irregular": "P10", "material": false, "metric": "moe_layer_cv", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null } ], "missing_cells": [], "passes_h1b": true, "passing_metrics": [ "padding_fraction", "R64" ], "verdict": "PASS" } ], "waste_contrasts": [ { "available": true, "ci95_high": -0.01613620902704422, "ci95_low": -0.018335446670663714, "coincident_efficiency_or_residual": true, "control": "P02", "efficiency_loss": 0.11608997226921058, "evaluable": true, "irregular": "P06", "material": false, "metric": "padding_fraction", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": -0.017218083890213506, "simultaneous_high": -0.0157356399373619, "simultaneous_low": -0.0187887535849442 }, { "available": true, "ci95_high": -0.026647777870177056, "ci95_low": -0.03356127646776247, "coincident_efficiency_or_residual": true, "control": "P02", "efficiency_loss": 0.11608997226921058, "evaluable": true, "irregular": "P06", "material": false, "metric": "graph_miss_rate", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": -0.03006598445684061, "simultaneous_high": -0.02530594241869426, "simultaneous_low": -0.03499903509242671 }, { "available": true, "ci95_high": -0.026633809539104453, "ci95_low": -0.033569133608294076, "coincident_efficiency_or_residual": true, "control": "P02", "efficiency_loss": 0.11608997226921058, "evaluable": true, "irregular": "P06", "material": false, "metric": "overflow_rate", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": -0.03006598445684061, "simultaneous_high": -0.025351137872591654, "simultaneous_low": -0.0349968653294319 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P02", "efficiency_loss": 0.11608997226921058, "evaluable": true, "irregular": "P06", "material": false, "metric": "mixed_interference", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null }, { "available": true, "ci95_high": 0.23494534783397408, "ci95_low": 0.2253590527218157, "coincident_efficiency_or_residual": true, "control": "P02", "efficiency_loss": 0.11608997226921058, "evaluable": true, "irregular": "P06", "material": true, "metric": "R64", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.2301483528866904, "simultaneous_high": 0.23683442206671917, "simultaneous_low": 0.22345003461028415 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P02", "efficiency_loss": 0.11608997226921058, "evaluable": true, "irregular": "P06", "material": false, "metric": "moe_layer_cv", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null }, { "available": true, "ci95_high": 0.0018881170209094382, "ci95_low": 0.00013272036050889215, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.2284629366493368, "evaluable": true, "irregular": "P06", "material": false, "metric": "padding_fraction", "p": 0.02776, "p_holm": 0.08327999999999999, "passes_h1b": false, "point": 0.001092906862063869, "simultaneous_high": 0.002162520644872445, "simultaneous_low": -0.0002871891115189649 }, { "available": true, "ci95_high": -0.000493778899366458, "ci95_low": -0.010138790500287403, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.2284629366493368, "evaluable": true, "irregular": "P06", "material": false, "metric": "graph_miss_rate", "p": 0.02632, "p_holm": 0.10528, "passes_h1b": false, "point": -0.004704030248702935, "simultaneous_high": 0.0009672756203671407, "simultaneous_low": -0.012632664546359583 }, { "available": true, "ci95_high": -0.0005068842298477604, "ci95_low": -0.010089468512164912, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.2284629366493368, "evaluable": true, "irregular": "P06", "material": false, "metric": "overflow_rate", "p": 0.02672, "p_holm": 0.10688, "passes_h1b": false, "point": -0.004704030248702935, "simultaneous_high": 0.0009123995960551078, "simultaneous_low": -0.012541358318390415 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.2284629366493368, "evaluable": true, "irregular": "P06", "material": false, "metric": "mixed_interference", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null }, { "available": true, "ci95_high": 0.3588237662068493, "ci95_low": 0.34996301147907066, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.2284629366493368, "evaluable": true, "irregular": "P06", "material": true, "metric": "R64", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.3543970834375052, "simultaneous_high": 0.3605880124391376, "simultaneous_low": 0.34826154238421436 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.2284629366493368, "evaluable": true, "irregular": "P06", "material": false, "metric": "moe_layer_cv", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null }, { "available": true, "ci95_high": 0.07258101928545771, "ci95_low": 0.06107199918894719, "coincident_efficiency_or_residual": true, "control": "P01", "efficiency_loss": 0.08324816211784114, "evaluable": true, "irregular": "P09", "material": true, "metric": "padding_fraction", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.0667290414201105, "simultaneous_high": 0.07492451384312424, "simultaneous_low": 0.058870086990988876 }, { "available": true, "ci95_high": -0.18669616533208697, "ci95_low": -0.21919298047891625, "coincident_efficiency_or_residual": true, "control": "P01", "efficiency_loss": 0.08324816211784114, "evaluable": true, "irregular": "P09", "material": false, "metric": "graph_miss_rate", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": -0.20308199280724987, "simultaneous_high": -0.18011971739412205, "simultaneous_low": -0.2256276809071987 }, { "available": true, "ci95_high": -0.18660802863031692, "ci95_low": -0.21934591413132573, "coincident_efficiency_or_residual": true, "control": "P01", "efficiency_loss": 0.08324816211784114, "evaluable": true, "irregular": "P09", "material": false, "metric": "overflow_rate", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": -0.20308199280724987, "simultaneous_high": -0.18035129413637946, "simultaneous_low": -0.22589311960316016 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P01", "efficiency_loss": 0.08324816211784114, "evaluable": true, "irregular": "P09", "material": false, "metric": "mixed_interference", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null }, { "available": true, "ci95_high": 0.4001054362524198, "ci95_low": 0.3922157126916775, "coincident_efficiency_or_residual": true, "control": "P01", "efficiency_loss": 0.08324816211784114, "evaluable": true, "irregular": "P09", "material": true, "metric": "R64", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.39616418510901036, "simultaneous_high": 0.4016625621683738, "simultaneous_low": 0.3906536566040832 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P01", "efficiency_loss": 0.08324816211784114, "evaluable": true, "irregular": "P09", "material": false, "metric": "moe_layer_cv", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null }, { "available": true, "ci95_high": 0.09130100661903304, "ci95_low": 0.07976380555258109, "coincident_efficiency_or_residual": false, "control": "P03", "efficiency_loss": 0.03840305601484284, "evaluable": true, "irregular": "P09", "material": true, "metric": "padding_fraction", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": 0.08542101015535679, "simultaneous_high": 0.09354749622519089, "simultaneous_low": 0.0776469398212851 }, { "available": true, "ci95_high": 0.03477003572235889, "ci95_low": 0.022150480290407913, "coincident_efficiency_or_residual": false, "control": "P03", "efficiency_loss": 0.03840305601484284, "evaluable": true, "irregular": "P09", "material": false, "metric": "graph_miss_rate", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": 0.027825216312380757, "simultaneous_high": 0.0379073029527558, "simultaneous_low": 0.020262740610606924 }, { "available": true, "ci95_high": 0.03478537546264273, "ci95_low": 0.022157030355767448, "coincident_efficiency_or_residual": false, "control": "P03", "efficiency_loss": 0.03840305601484284, "evaluable": true, "irregular": "P09", "material": false, "metric": "overflow_rate", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": 0.027825216312380757, "simultaneous_high": 0.038155569680251286, "simultaneous_low": 0.020260913333777324 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": false, "control": "P03", "efficiency_loss": 0.03840305601484284, "evaluable": true, "irregular": "P09", "material": false, "metric": "mixed_interference", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null }, { "available": true, "ci95_high": 0.5238722090454428, "ci95_low": 0.5169233936643203, "coincident_efficiency_or_residual": false, "control": "P03", "efficiency_loss": 0.03840305601484284, "evaluable": true, "irregular": "P09", "material": true, "metric": "R64", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": 0.5204129156598252, "simultaneous_high": 0.5252564301232907, "simultaneous_low": 0.5155191519515977 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": false, "control": "P03", "efficiency_loss": 0.03840305601484284, "evaluable": true, "irregular": "P09", "material": false, "metric": "moe_layer_cv", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null }, { "available": true, "ci95_high": 0.08855777444708128, "ci95_low": 0.027415277773332525, "coincident_efficiency_or_residual": true, "control": "P03", "efficiency_loss": 0.4469310402722787, "evaluable": true, "irregular": "P10", "material": true, "metric": "padding_fraction", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.05565211993295673, "simultaneous_high": 0.10341073102256013, "simultaneous_low": 0.020097017796153225 }, { "available": true, "ci95_high": -0.00601669947733407, "ci95_low": -0.009872845681590466, "coincident_efficiency_or_residual": true, "control": "P03", "efficiency_loss": 0.4469310402722787, "evaluable": true, "irregular": "P10", "material": false, "metric": "graph_miss_rate", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": -0.008145427700863333, "simultaneous_high": -0.0049986468588015505, "simultaneous_low": -0.010459290275607078 }, { "available": true, "ci95_high": -0.006012535696644192, "ci95_low": -0.00989506245698499, "coincident_efficiency_or_residual": true, "control": "P03", "efficiency_loss": 0.4469310402722787, "evaluable": true, "irregular": "P10", "material": false, "metric": "overflow_rate", "p": 0.0, "p_holm": 0.0, "passes_h1b": false, "point": -0.008145427700863333, "simultaneous_high": -0.005013934447667286, "simultaneous_low": -0.010471471437559795 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P03", "efficiency_loss": 0.4469310402722787, "evaluable": true, "irregular": "P10", "material": false, "metric": "mixed_interference", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null }, { "available": true, "ci95_high": 0.4561736305824604, "ci95_low": 0.43955479496868705, "coincident_efficiency_or_residual": true, "control": "P03", "efficiency_loss": 0.4469310402722787, "evaluable": true, "irregular": "P10", "material": true, "metric": "R64", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.4478716685574937, "simultaneous_high": 0.459713780733712, "simultaneous_low": 0.43635435003093426 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P03", "efficiency_loss": 0.4469310402722787, "evaluable": true, "irregular": "P10", "material": false, "metric": "moe_layer_cv", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null }, { "available": true, "ci95_high": 0.08668052314167546, "ci95_low": 0.025823274229141942, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.1425966128421564, "evaluable": true, "irregular": "P10", "material": true, "metric": "padding_fraction", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.05398526806052646, "simultaneous_high": 0.10213016668480329, "simultaneous_low": 0.018683381445978635 }, { "available": true, "ci95_high": 0.0007610647800286464, "ci95_low": -0.00936641415445055, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.1425966128421564, "evaluable": true, "irregular": "P10", "material": false, "metric": "graph_miss_rate", "p": 0.10722, "p_holm": 0.32166, "passes_h1b": false, "point": -0.0037955725000514817, "simultaneous_high": 0.0023548687154005257, "simultaneous_low": -0.011962189207249601 }, { "available": true, "ci95_high": 0.0007651798910721392, "ci95_low": -0.009350365146339001, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.1425966128421564, "evaluable": true, "irregular": "P10", "material": false, "metric": "overflow_rate", "p": 0.10804, "p_holm": 0.32411999999999996, "passes_h1b": false, "point": -0.0037955725000514817, "simultaneous_high": 0.0023480385252717118, "simultaneous_low": -0.011930615598005356 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.1425966128421564, "evaluable": true, "irregular": "P10", "material": false, "metric": "mixed_interference", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null }, { "available": true, "ci95_high": 0.45618061702156487, "ci95_low": 0.4395710696329076, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.1425966128421564, "evaluable": true, "irregular": "P10", "material": true, "metric": "R64", "p": 0.0, "p_holm": 0.0, "passes_h1b": true, "point": 0.4478716685574937, "simultaneous_high": 0.4594884290583298, "simultaneous_low": 0.4363807227134572 }, { "available": false, "ci95_high": null, "ci95_low": null, "coincident_efficiency_or_residual": true, "control": "P04", "efficiency_loss": 0.1425966128421564, "evaluable": true, "irregular": "P10", "material": false, "metric": "moe_layer_cv", "p": 1.0, "p_holm": 1.0, "passes_h1b": false, "point": null, "simultaneous_high": null, "simultaneous_low": null } ], "waste_thresholds": { "R64": 0.15, "graph_miss_rate": 0.1, "mixed_interference": 0.1, "moe_layer_cv": 0.15, "overflow_rate": 0.1, "padding_fraction": 0.05 } }