{ "contrast_decomposition": { "exact_state_matched_tp8_minus_tp4_ms": 10.902788634037428, "residual_vs_exact_iteration_ms": 1.7850640558340523, "residual_vs_frozen_real_tpot_ms": 3.9527886340374287, "simulator_internal_tp8_minus_tp4_ms": -20.06625468177714, "state_composition_shift_ms": 30.969043315814567 }, "exact_state_matched": { "configs": { "tp4_ep1_mns64": { "components_ms": { "attention": 7.861372580683772, "dense_mlp_compute": 0.20457670875208997, "ep_communication": 0.0, "moe_compute": 11.818199308522054, "moe_routing": 1.3660523028556315, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 34.25746674314369, "tp_dp_communication": 13.007265841334672 }, "coverage": 1.0, "supported_decode_tokens": 32895, "total_decode_tokens": 32895, "unsupported": {} }, "tp8_ep8_mns64": { "components_ms": { "attention": 5.730952171784399, "dense_mlp_compute": 0.17382455581232167, "ep_communication": 6.535508227248577, "moe_compute": 9.840752983018692, "moe_routing": 1.5044582710663996, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 45.160255377181116, "tp_dp_communication": 6.535508227248577 }, "coverage": 1.0, "supported_decode_tokens": 32895, "total_decode_tokens": 32895, "unsupported": {} } }, "method": "decode-token-weighted exact (context_tokens, generation_requests) composition from vLLM iteration details; no interpolation", "tp8_minus_tp4_ms": { "attention": -2.130420408899373, "dense_mlp_compute": -0.030752152939768296, "ep_communication": 6.535508227248577, "moe_compute": -1.9774463255033616, "moe_routing": 0.13840596821076812, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 10.902788634037428, "tp_dp_communication": -6.471757614086094 } }, "proxy_matched": { "configs": { "tp4_ep1_mns64": { "components_ms": { "attention": 6.303822560333333, "dense_mlp_compute": 0.17883562666666666, "ep_communication": 0.0, "moe_compute": 26.449277218333332, "moe_routing": 1.2571787503333332, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 46.414892970000004, "tp_dp_communication": 12.225778813333333 }, "coverage": 1.0, "supported_samples": 45, "total_samples": 45, "unsupported": {} }, "tp8_ep8_mns64": { "components_ms": { "attention": 6.063134093052075, "dense_mlp_compute": 0.18060032000000073, "ep_communication": 6.824791048020123, "moe_compute": 10.391190702777717, "moe_routing": 1.5681029842793537, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 37.86318467071363, "tp_dp_communication": 6.824791048020123 }, "coverage": 1.0, "supported_samples": 21, "total_samples": 21, "unsupported": {} } }, "method": "exact batch-size lookup; each simulator config is reweighted to its own frozen-real steady Running histogram; no interpolation", "tp8_minus_tp4_ms": { "attention": -0.2406884672812577, "dense_mlp_compute": 0.0017646933333340664, "ep_communication": 6.824791048020123, "moe_compute": -16.058086515555615, "moe_routing": 0.31092423394602053, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -8.551708299286375, "tp_dp_communication": -5.40098776531321 } }, "real": { "tp4_ep1_mns64": { "aggregate": { "generation_tokens_per_s": { "cv": 0.01219623132338527, "distinct_n": 32, "max": 217.3, "mean": 204.7488888888889, "min": 197.1, "n": 45 }, "kv_percent": { "cv": 0.09908502666308305, "distinct_n": 2, "max": 5.6, "mean": 5.233333333333333, "min": 4.5, "n": 45 }, "running": { "cv": 0.10101525445522107, "distinct_n": 2, "max": 5.0, "mean": 4.666666666666667, "min": 4.0, "n": 45 }, "running_histogram": { "4": 15, "5": 30 }, "samples": 45, "waiting": { "cv": 0.0, "distinct_n": 1, "max": 0.0, "mean": 0.0, "min": 0.0, "n": 45 } }, "proxy_only": true, "steady_rule": "prompt throughput >= 95% of 3276.8 tokens/s", "trials": [ { "all_samples": 17, "generation_tokens_per_s": { "cv": 0.01635665678820842, "distinct_n": 13, "max": 217.3, "mean": 205.58666666666667, "min": 202.4, "n": 15 }, "kv_percent": { "cv": 0.0, "distinct_n": 1, "max": 5.6, "mean": 5.6, "min": 5.6, "n": 15 }, "path": "/home/admin/cpfs/wjh/aituner/qwen235-v020-fourcase-20260719-r1/real/fixed-pd/real/tp4_ep1_mns64/trial1/logs/server.log", "running": { "cv": 0.0, "distinct_n": 1, "max": 5.0, "mean": 5.0, "min": 5.0, "n": 15 }, "steady_samples": 15, "trial": "trial1", "waiting": { "cv": 0.0, "distinct_n": 1, "max": 0.0, "mean": 0.0, "min": 0.0, "n": 15 } }, { "all_samples": 17, "generation_tokens_per_s": { "cv": 0.01101205870299425, "distinct_n": 11, "max": 206.3, "mean": 204.18666666666667, "min": 197.1, "n": 15 }, "kv_percent": { "cv": 0.0, "distinct_n": 1, "max": 5.6, "mean": 5.6, "min": 5.6, "n": 15 }, "path": "/home/admin/cpfs/wjh/aituner/qwen235-v020-fourcase-20260719-r1/real/fixed-pd/real/tp4_ep1_mns64/trial2/logs/server.log", "running": { "cv": 0.0, "distinct_n": 1, "max": 5.0, "mean": 5.0, "min": 5.0, "n": 15 }, "steady_samples": 15, "trial": "trial2", "waiting": { "cv": 0.0, "distinct_n": 1, "max": 0.0, "mean": 0.0, "min": 0.0, "n": 15 } }, { "all_samples": 17, "generation_tokens_per_s": { "cv": 0.005467774668645034, "distinct_n": 14, "max": 206.0, "mean": 204.47333333333333, "min": 202.0, "n": 15 }, "kv_percent": { "cv": 0.0, "distinct_n": 1, "max": 4.5, "mean": 4.5, "min": 4.5, "n": 15 }, "path": "/home/admin/cpfs/wjh/aituner/qwen235-v020-fourcase-20260719-r1/real/fixed-pd/real/tp4_ep1_mns64/trial3/logs/server.log", "running": { "cv": 0.0, "distinct_n": 1, "max": 4.0, "mean": 4.0, "min": 4.0, "n": 15 }, "steady_samples": 15, "trial": "trial3", "waiting": { "cv": 0.0, "distinct_n": 1, "max": 0.0, "mean": 0.0, "min": 0.0, "n": 15 } } ] }, "tp8_ep8_mns64": { "aggregate": { "generation_tokens_per_s": { "cv": 0.01855015540813005, "distinct_n": 21, "max": 415.7, "mean": 406.5380952380952, "min": 390.8, "n": 21 }, "kv_percent": { "cv": 0.03973151445031385, "distinct_n": 3, "max": 5.6, "mean": 5.295238095238095, "min": 4.8, "n": 21 }, "running": { "cv": 0.04297805843263526, "distinct_n": 3, "max": 13.0, "mean": 12.238095238095237, "min": 11.0, "n": 21 }, "running_histogram": { "11": 1, "12": 14, "13": 6 }, "samples": 21, "waiting": { "cv": 0.0, "distinct_n": 1, "max": 0.0, "mean": 0.0, "min": 0.0, "n": 21 } }, "proxy_only": true, "steady_rule": "prompt throughput >= 95% of 6553.6 tokens/s", "trials": [ { "all_samples": 9, "generation_tokens_per_s": { "cv": 0.018873398222858283, "distinct_n": 7, "max": 415.7, "mean": 406.87142857142857, "min": 392.3, "n": 7 }, "kv_percent": { "cv": 0.03400298559320833, "distinct_n": 2, "max": 5.6, "mean": 5.314285714285715, "min": 5.2, "n": 7 }, "path": "/home/admin/cpfs/wjh/aituner/qwen235-v020-fourcase-20260719-r1/real/fixed-pd/real/tp8_ep8_mns64/trial1/logs/server.log", "running": { "cv": 0.036770670467074176, "distinct_n": 2, "max": 13.0, "mean": 12.285714285714286, "min": 12.0, "n": 7 }, "steady_samples": 7, "trial": "trial1", "waiting": { "cv": 0.0, "distinct_n": 1, "max": 0.0, "mean": 0.0, "min": 0.0, "n": 7 } }, { "all_samples": 9, "generation_tokens_per_s": { "cv": 0.01869328742146201, "distinct_n": 7, "max": 412.9, "mean": 406.2857142857143, "min": 390.8, "n": 7 }, "kv_percent": { "cv": 0.04861017342390845, "distinct_n": 3, "max": 5.6, "mean": 5.257142857142857, "min": 4.8, "n": 7 }, "path": "/home/admin/cpfs/wjh/aituner/qwen235-v020-fourcase-20260719-r1/real/fixed-pd/real/tp8_ep8_mns64/trial2/logs/server.log", "running": { "cv": 0.052613364176465637, "distinct_n": 3, "max": 13.0, "mean": 12.142857142857142, "min": 11.0, "n": 7 }, "steady_samples": 7, "trial": "trial2", "waiting": { "cv": 0.0, "distinct_n": 1, "max": 0.0, "mean": 0.0, "min": 0.0, "n": 7 } }, { "all_samples": 9, "generation_tokens_per_s": { "cv": 0.018043345382112573, "distinct_n": 7, "max": 414.9, "mean": 406.45714285714286, "min": 393.0, "n": 7 }, "kv_percent": { "cv": 0.03400298559320833, "distinct_n": 2, "max": 5.6, "mean": 5.314285714285715, "min": 5.2, "n": 7 }, "path": "/home/admin/cpfs/wjh/aituner/qwen235-v020-fourcase-20260719-r1/real/fixed-pd/real/tp8_ep8_mns64/trial3/logs/server.log", "running": { "cv": 0.036770670467074176, "distinct_n": 2, "max": 13.0, "mean": 12.285714285714286, "min": 12.0, "n": 7 }, "steady_samples": 7, "trial": "trial3", "waiting": { "cv": 0.0, "distinct_n": 1, "max": 0.0, "mean": 0.0, "min": 0.0, "n": 7 } } ] } }, "real_iteration_state": { "tp4_ep1_mns64": { "decode_batch_size": { "cv": 0.13029119433004072, "distinct_n": 5, "max": 5.0, "mean": 3.8896771904930825, "min": 1.0, "n": 8457 }, "decode_bearing_rows": 8457, "decode_token_weighted_iteration_elapsed_ms": 18.47097461620307, "decode_token_weighted_joint_state_histogram": { "0:1": 149, "0:2": 280, "0:3": 621, "0:4": 31012, "0:5": 400, "4096:1": 1, "4096:2": 2, "4096:3": 222, "4096:4": 208 }, "measured_rows": 8460, "mixed_iteration_elapsed_ms": { "cv": 0.015940570375581706, "distinct_n": 114, "max": 350.16, "mean": 337.35875, "min": 331.36, "n": 128 }, "mixed_prefill_decode_rows": 128, "path": "/home/admin/cpfs/wjh/aituner/qwen235-fixed-pd-state-diagnosis-20260719-r1/iteration-real/tp4_ep1_mns64/logs/server.log", "pure_decode_batch_histogram": { "1": 149, "2": 140, "3": 207, "4": 7753, "5": 80 }, "pure_decode_iteration_elapsed_ms": { "cv": 0.0683725733639485, "distinct_n": 353, "max": 63.66, "mean": 14.141689278424781, "min": 0.11, "n": 8329 }, "pure_decode_rows": 8329 }, "tp8_ep8_mns64": { "decode_batch_size": { "cv": 0.24310653962915885, "distinct_n": 13, "max": 13.0, "mean": 10.921314741035857, "min": 1.0, "n": 3012 }, "decode_bearing_rows": 3012, "decode_token_weighted_iteration_elapsed_ms": 27.588699194406445, "decode_token_weighted_joint_state_histogram": { "0:1": 49, "0:10": 700, "0:11": 2431, "0:12": 24312, "0:13": 2067, "0:2": 96, "0:3": 138, "0:4": 196, "0:5": 215, "0:6": 270, "0:7": 315, "0:8": 352, "0:9": 351, "4096:1": 1, "4096:10": 40, "4096:11": 682, "4096:12": 636, "4096:2": 2, "4096:3": 3, "4096:4": 4, "4096:5": 5, "4096:6": 6, "4096:7": 7, "4096:8": 8, "4096:9": 9 }, "measured_rows": 3015, "mixed_iteration_elapsed_ms": { "cv": 0.04096511316969508, "distinct_n": 126, "max": 345.82, "mean": 319.430703125, "min": 294.13, "n": 128 }, "mixed_prefill_decode_rows": 128, "path": "/home/admin/cpfs/wjh/aituner/qwen235-fixed-pd-state-diagnosis-20260719-r1/iteration-real/tp8_ep8_mns64/logs/server.log", "pure_decode_batch_histogram": { "1": 49, "10": 70, "11": 221, "12": 2026, "13": 159, "2": 48, "3": 46, "4": 49, "5": 43, "6": 45, "7": 45, "8": 44, "9": 39 }, "pure_decode_iteration_elapsed_ms": { "cv": 0.08468104731049882, "distinct_n": 347, "max": 20.05, "mean": 14.330596393897366, "min": 9.46, "n": 2884 }, "pure_decode_rows": 2884 } }, "reference": { "exact_iteration_tp8_minus_tp4_ms": 9.117724578203376, "observed_real_tp8_minus_tp4_ms": 6.949999999999999, "real_tpot_ms": { "tp4_ep1_mns64": 21.0442, "tp8_ep8_mns64": 27.9942 } }, "same_batch_contrasts": { "1": { "tp4_n": 54, "tp8_minus_tp4_ms": { "attention": -0.8935417788173714, "dense_mlp_compute": 5.551115123125783e-17, "ep_communication": 7.6409967723488785, "moe_compute": -1.3674890128222263, "moe_routing": 0.24700169495130986, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -8.382111054979667, "tp_dp_communication": -6.785968403651121 }, "tp8_n": 34 }, "10": { "tp4_n": 38, "tp8_minus_tp4_ms": { "attention": -0.9062451258095203, "dense_mlp_compute": 7.216449660063518e-16, "ep_communication": 6.824791048020123, "moe_compute": -30.78018275622229, "moe_routing": 0.27075982727935366, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -23.288943843339915, "tp_dp_communication": -4.708641311979878 }, "tp8_n": 22 }, "11": { "tp4_n": 42, "tp8_minus_tp4_ms": { "attention": -0.90756947260952, "dense_mlp_compute": 7.216449660063518e-16, "ep_communication": 6.824791048020123, "moe_compute": -30.78018275622229, "moe_routing": 0.2707598272793539, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -23.29026819009679, "tp_dp_communication": -4.708641311979878 }, "tp8_n": 22 }, "12": { "tp4_n": 46, "tp8_minus_tp4_ms": { "attention": -0.90756947260952, "dense_mlp_compute": 7.216449660063518e-16, "ep_communication": 6.824791048020123, "moe_compute": -30.780182756222285, "moe_routing": 0.27075982727935366, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -23.290268190109693, "tp_dp_communication": -4.708641311979878 }, "tp8_n": 21 }, "13": { "tp4_n": 46, "tp8_minus_tp4_ms": { "attention": -0.9271714387939403, "dense_mlp_compute": 7.771561172376096e-16, "ep_communication": 6.824791048020123, "moe_compute": -30.78018275622228, "moe_routing": 0.27075982727935366, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -23.309870155730238, "tp_dp_communication": -4.708641311979878 }, "tp8_n": 22 }, "14": { "tp4_n": 47, "tp8_minus_tp4_ms": { "attention": -0.9273699663939379, "dense_mlp_compute": 6.938893903907228e-16, "ep_communication": 6.824791048020123, "moe_compute": -30.78018275622229, "moe_routing": 0.27075982727935366, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -23.310068683979324, "tp_dp_communication": -4.708641311979878 }, "tp8_n": 21 }, "15": { "tp4_n": 663, "tp8_minus_tp4_ms": { "attention": -0.9280176641939368, "dense_mlp_compute": 6.938893903907228e-16, "ep_communication": 6.824791048020124, "moe_compute": -30.78018275622229, "moe_routing": 0.2707598272793539, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -23.310716381302065, "tp_dp_communication": -4.708641311979875 }, "tp8_n": 21 }, "16": { "tp4_n": 1053, "tp8_minus_tp4_ms": { "attention": -0.9280176641939377, "dense_mlp_compute": 7.216449660063518e-16, "ep_communication": 6.824791048020123, "moe_compute": -30.78018275622229, "moe_routing": 0.27075982727935366, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -23.310716381309007, "tp_dp_communication": -4.708641311979878 }, "tp8_n": 22 }, "2": { "tp4_n": 52, "tp8_minus_tp4_ms": { "attention": -0.893056937985337, "dense_mlp_compute": 5.551115123125783e-17, "ep_communication": 7.170214735418557, "moe_compute": -2.487079396822226, "moe_routing": 0.23761673495131297, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -7.529038359797266, "tp_dp_communication": -6.276494110581443 }, "tp8_n": 32 }, "3": { "tp4_n": 47, "tp8_minus_tp4_ms": { "attention": -0.8994740207853011, "dense_mlp_compute": 8.326672684688674e-17, "ep_communication": 6.661276281625032, "moe_compute": -4.971655204025423, "moe_routing": 0.23007132819364218, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -9.72273303992905, "tp_dp_communication": -6.0593006383749675 }, "tp8_n": 31 }, "4": { "tp4_n": 48, "tp8_minus_tp4_ms": { "attention": -0.9032519198967934, "dense_mlp_compute": 5.551115123125783e-17, "ep_communication": 6.661276281625032, "moe_compute": -4.971655204025423, "moe_routing": 0.23007132819364196, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -9.726510939439532, "tp_dp_communication": -6.0593006383749675 }, "tp8_n": 30 }, "5": { "tp4_n": 34, "tp8_minus_tp4_ms": { "attention": -0.8975988783634543, "dense_mlp_compute": 7.494005416219807e-16, "ep_communication": 6.619871115982532, "moe_compute": -25.90819860140641, "moe_routing": 0.2783929890825345, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -28.211543726727538, "tp_dp_communication": -5.358508644017467 }, "tp8_n": 27 }, "6": { "tp4_n": 33, "tp8_minus_tp4_ms": { "attention": -0.8977163413634548, "dense_mlp_compute": 7.216449660063518e-16, "ep_communication": 6.619871115982532, "moe_compute": -25.90819860140641, "moe_routing": 0.2783929890825343, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -28.211661189448645, "tp_dp_communication": -5.358508644017467 }, "tp8_n": 26 }, "7": { "tp4_n": 34, "tp8_minus_tp4_ms": { "attention": -0.9209473308539557, "dense_mlp_compute": 7.216449660063518e-16, "ep_communication": 6.619871115982532, "moe_compute": -25.908198601406404, "moe_routing": 0.2783929890825345, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -28.23489217903426, "tp_dp_communication": -5.358508644017467 }, "tp8_n": 26 }, "8": { "tp4_n": 33, "tp8_minus_tp4_ms": { "attention": -0.9209473308539557, "dense_mlp_compute": 7.216449660063518e-16, "ep_communication": 6.619871115982532, "moe_compute": -25.90819860140641, "moe_routing": 0.27839298908253474, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -28.23489217902994, "tp_dp_communication": -5.358508644017467 }, "tp8_n": 27 }, "9": { "tp4_n": 32, "tp8_minus_tp4_ms": { "attention": -0.9096465718095201, "dense_mlp_compute": 7.216449660063518e-16, "ep_communication": 6.824791048020123, "moe_compute": -30.78018275622229, "moe_routing": 0.27075982727935366, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -23.292345289360462, "tp_dp_communication": -4.708641311979878 }, "tp8_n": 21 } }, "schema": "qwen235-fixed-pd-state-diagnosis-v1", "scope": { "graph_observability": "Frontier state outputs have no direct graph bucket/padding/launch-overhead field; graph effects remain folded into predictors", "op_trace_accounting": "For TP8 shared-domain sync, total is ledger stage_end-start (critical path); op categories are serialized work estimates and are not additive because overlap and lane-summed wait diagnostics are represented separately", "real_proxy_limitation": "vLLM 10-second Running is active requests, not per-iteration decode batch; context lengths and graph buckets are unavailable in frozen logs", "workload": "Fixed-PD 4096->256, 0.2 req/s/GPU, MNS64" }, "simulator": { "tp4_ep1_mns64": { "batch_support": { "1": { "components_ms": { "attention": 5.918822475999999, "dense_mlp_compute": 0.177568256, "ep_communication": 0.0, "moe_compute": 4.277032336, "moe_routing": 1.234618249, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 26.035006493, "tp_dp_communication": 14.426965176 }, "n": 54 }, "10": { "components_ms": { "attention": 6.795322718, "dense_mlp_compute": 0.18060032, "ep_communication": 0.0, "moe_compute": 41.171373459, "moe_routing": 1.297343157, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 60.978072013, "tp_dp_communication": 11.53343236 }, "n": 38 }, "11": { "components_ms": { "attention": 6.8427973799999995, "dense_mlp_compute": 0.18060032, "ep_communication": 0.0, "moe_compute": 41.171373459, "moe_routing": 1.297343157, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 61.025546675, "tp_dp_communication": 11.53343236 }, "n": 42 }, "12": { "components_ms": { "attention": 6.84279738, "dense_mlp_compute": 0.18060032, "ep_communication": 0.0, "moe_compute": 41.171373459, "moe_routing": 1.297343157, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 61.02554667500001, "tp_dp_communication": 11.53343236 }, "n": 46 }, "13": { "components_ms": { "attention": 7.310070996000001, "dense_mlp_compute": 0.18060031999999998, "ep_communication": 0.0, "moe_compute": 41.171373458999994, "moe_routing": 1.297343157, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 61.492820290999994, "tp_dp_communication": 11.53343236 }, "n": 46 }, "14": { "components_ms": { "attention": 7.316185658, "dense_mlp_compute": 0.18060032000000004, "ep_communication": 0.0, "moe_compute": 41.171373459, "moe_routing": 1.297343157, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 61.49893495300001, "tp_dp_communication": 11.53343236 }, "n": 47 }, "15": { "components_ms": { "attention": 7.332662654999999, "dense_mlp_compute": 0.18060032000000004, "ep_communication": 0.0, "moe_compute": 41.171373459, "moe_routing": 1.297343157, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 61.51541195, "tp_dp_communication": 11.533432359999999 }, "n": 663 }, "16": { "components_ms": { "attention": 7.332662655, "dense_mlp_compute": 0.18060032, "ep_communication": 0.0, "moe_compute": 41.171373459, "moe_routing": 1.297343157, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 61.51541195, "tp_dp_communication": 11.53343236 }, "n": 1053 }, "2": { "components_ms": { "attention": 6.048001424230768, "dense_mlp_compute": 0.177568256, "ep_communication": 0.0, "moe_compute": 5.39662272, "moe_routing": 1.237987209, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 26.30688845623077, "tp_dp_communication": 13.446708846 }, "n": 52 }, "3": { "components_ms": { "attention": 6.09964707180851, "dense_mlp_compute": 0.177568256, "ep_communication": 0.0, "moe_compute": 9.978847425, "moe_routing": 1.2434858329999998, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 30.22012550680851, "tp_dp_communication": 12.72057692 }, "n": 47 }, "4": { "components_ms": { "attention": 6.285367077, "dense_mlp_compute": 0.177568256, "ep_communication": 0.0, "moe_compute": 9.978847425, "moe_routing": 1.243485833, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 30.405845512, "tp_dp_communication": 12.72057692 }, "n": 48 }, "5": { "components_ms": { "attention": 6.313050302, "dense_mlp_compute": 0.17946931199999996, "ep_communication": 0.0, "moe_compute": 34.684492115, "moe_routing": 1.264025209, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 54.419416699, "tp_dp_communication": 11.97837976 }, "n": 34 }, "6": { "components_ms": { "attention": 6.356479957, "dense_mlp_compute": 0.179469312, "ep_communication": 0.0, "moe_compute": 34.684492115, "moe_routing": 1.264025209, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 54.462846354, "tp_dp_communication": 11.97837976 }, "n": 33 }, "7": { "components_ms": { "attention": 6.734075413, "dense_mlp_compute": 0.179469312, "ep_communication": 0.0, "moe_compute": 34.68449211499999, "moe_routing": 1.264025209, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 54.84044181, "tp_dp_communication": 11.97837976 }, "n": 34 }, "8": { "components_ms": { "attention": 6.734075413, "dense_mlp_compute": 0.179469312, "ep_communication": 0.0, "moe_compute": 34.684492115, "moe_routing": 1.264025209, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 54.84044181, "tp_dp_communication": 11.97837976 }, "n": 33 }, "9": { "components_ms": { "attention": 6.782511044, "dense_mlp_compute": 0.18060032, "ep_communication": 0.0, "moe_compute": 41.171373459, "moe_routing": 1.297343157, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 60.965260339, "tp_dp_communication": 11.53343236 }, "n": 32 } }, "component_source": "stage_batch_ledger", "decode_batch_size": { "cv": 0.3076467178753811, "distinct_n": 16, "max": 16.0, "mean": 13.537037037037036, "min": 1.0, "n": 2430 }, "decode_bearing_rows": 2430, "decode_token_weighted_all_step_components_ms": { "attention": 13.842547047292292, "dense_mlp_compute": 0.2927251518073871, "ep_communication": 0.0, "moe_compute": 45.47878637854458, "moe_routing": 1.8023597240381213, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 74.2229273813438, "tp_dp_communication": 12.806509080469617 }, "decode_token_weighted_mixed_step_share": 0.05481076151390789, "mixed_prefill_decode_rows": 128, "pure_decode_rows": 2302, "pure_decode_token_weighted_components_ms": { "attention": 7.263972797140871, "dense_mlp_compute": 0.18052079084832112, "ep_communication": 0.0, "moe_compute": 40.472043520877655, "moe_routing": 1.2955265717923583, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 60.78208599545992, "tp_dp_communication": 11.57002231571491 }, "scorer_equivalence": { "base_metrics": { "e2e_mean_ms": 19261.684938205322, "e2e_p50_ms": 19681.421068277567, "e2e_p90_ms": 19712.678973231064, "e2e_p95_ms": 19717.18006692948, "slos": { "tpot_100ms": { "feasible": true, "pass_rate": 1.0, "passed": 129 }, "tpot_150ms": { "feasible": true, "pass_rate": 1.0, "passed": 129 }, "tpot_180ms": { "feasible": true, "pass_rate": 1.0, "passed": 129 }, "tpot_50ms": { "feasible": false, "pass_rate": 0.0, "passed": 0 } }, "tpot_mean_ms": 74.22292738142716, "tpot_p50_ms": 75.8976524911963, "tpot_p90_ms": 75.8976524912086, "tpot_p95_ms": 75.89765249120967, "ttft_mean_ms": 334.8384559413977, "ttft_p50_ms": 334.75193988430976, "ttft_p90_ms": 359.7779859328796, "ttft_p95_ms": 363.2786816744229 }, "request_metrics_byte_identical": true, "request_metrics_sha256": "01ed41e9babf2eb71286e93d8f4986dda9820f92212c975ed9411a95a5f8758f" }, "stage_rows": 2431, "trace_validation": null }, "tp8_ep8_mns64": { "batch_support": { "1": { "components_ms": { "attention": 5.025280697182628, "dense_mlp_compute": 0.17756825600000006, "ep_communication": 7.6409967723488785, "moe_compute": 2.909543323177774, "moe_routing": 1.4816199439513098, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 17.652895438020334, "tp_dp_communication": 7.6409967723488785 }, "n": 34 }, "10": { "components_ms": { "attention": 5.88907759219048, "dense_mlp_compute": 0.18060032000000073, "ep_communication": 6.824791048020123, "moe_compute": 10.391190702777715, "moe_routing": 1.5681029842793537, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 37.68912816966009, "tp_dp_communication": 6.824791048020123 }, "n": 22 }, "11": { "components_ms": { "attention": 5.9352279073904795, "dense_mlp_compute": 0.18060032000000073, "ep_communication": 6.824791048020123, "moe_compute": 10.391190702777715, "moe_routing": 1.568102984279354, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 37.73527848490321, "tp_dp_communication": 6.824791048020123 }, "n": 22 }, "12": { "components_ms": { "attention": 5.93522790739048, "dense_mlp_compute": 0.18060032000000073, "ep_communication": 6.824791048020123, "moe_compute": 10.391190702777717, "moe_routing": 1.5681029842793537, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 37.735278484890316, "tp_dp_communication": 6.824791048020123 }, "n": 21 }, "13": { "components_ms": { "attention": 6.382899557206061, "dense_mlp_compute": 0.18060032000000076, "ep_communication": 6.824791048020123, "moe_compute": 10.391190702777715, "moe_routing": 1.5681029842793537, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 38.182950135269756, "tp_dp_communication": 6.824791048020123 }, "n": 22 }, "14": { "components_ms": { "attention": 6.388815691606062, "dense_mlp_compute": 0.18060032000000073, "ep_communication": 6.824791048020123, "moe_compute": 10.391190702777715, "moe_routing": 1.5681029842793537, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 38.188866269020686, "tp_dp_communication": 6.824791048020123 }, "n": 21 }, "15": { "components_ms": { "attention": 6.404644990806062, "dense_mlp_compute": 0.18060032000000073, "ep_communication": 6.824791048020124, "moe_compute": 10.391190702777713, "moe_routing": 1.568102984279354, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 38.204695568697936, "tp_dp_communication": 6.824791048020124 }, "n": 21 }, "16": { "components_ms": { "attention": 6.404644990806062, "dense_mlp_compute": 0.18060032000000073, "ep_communication": 6.824791048020123, "moe_compute": 10.391190702777715, "moe_routing": 1.5681029842793537, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 38.204695568690994, "tp_dp_communication": 6.824791048020123 }, "n": 22 }, "17": { "components_ms": { "attention": 6.652331067872723, "dense_mlp_compute": 0.18267583999999898, "ep_communication": 6.763788700699805, "moe_compute": 14.63356500064447, "moe_routing": 1.647955106498404, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 39.2554552675483, "tp_dp_communication": 6.763788700699805 }, "n": 31 }, "18": { "components_ms": { "attention": 6.652331067872723, "dense_mlp_compute": 0.18267583999999898, "ep_communication": 6.763788700699805, "moe_compute": 14.633565000644474, "moe_routing": 1.647955106498404, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 39.25545526754183, "tp_dp_communication": 6.763788700699805 }, "n": 30 }, "19": { "components_ms": { "attention": 6.652331067872723, "dense_mlp_compute": 0.18267583999999898, "ep_communication": 6.763788700699805, "moe_compute": 14.633565000644472, "moe_routing": 1.647955106498404, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 39.25545526755436, "tp_dp_communication": 6.763788700699805 }, "n": 32 }, "2": { "components_ms": { "attention": 5.154944486245431, "dense_mlp_compute": 0.17756825600000006, "ep_communication": 7.170214735418557, "moe_compute": 2.909543323177774, "moe_routing": 1.475603943951313, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 18.777850096433504, "tp_dp_communication": 7.170214735418557 }, "n": 32 }, "20": { "components_ms": { "attention": 6.652331067872723, "dense_mlp_compute": 0.18267583999999898, "ep_communication": 6.763788700699804, "moe_compute": 14.633565000644472, "moe_routing": 1.6479551064984042, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 39.25545526756006, "tp_dp_communication": 6.763788700699804 }, "n": 33 }, "21": { "components_ms": { "attention": 6.9837604522698395, "dense_mlp_compute": 0.18267583999999895, "ep_communication": 6.763788700699806, "moe_compute": 14.633565000644474, "moe_routing": 1.6479551064984037, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 39.58688465210873, "tp_dp_communication": 6.763788700699806 }, "n": 37 }, "22": { "components_ms": { "attention": 6.9837604522698395, "dense_mlp_compute": 0.18267583999999898, "ep_communication": 6.763788700699805, "moe_compute": 14.633565000644472, "moe_routing": 1.6479551064984042, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 39.586884652057584, "tp_dp_communication": 6.763788700699805 }, "n": 51 }, "23": { "components_ms": { "attention": 6.9837604522698395, "dense_mlp_compute": 0.182675839999999, "ep_communication": 6.763788700699805, "moe_compute": 14.63356500064447, "moe_routing": 1.647955106498404, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 39.58688465207786, "tp_dp_communication": 6.763788700699805 }, "n": 906 }, "24": { "components_ms": { "attention": 6.9837604522698395, "dense_mlp_compute": 0.18267583999999895, "ep_communication": 6.763788700699805, "moe_compute": 14.633565000644472, "moe_routing": 1.6479551064984037, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 39.58688465207813, "tp_dp_communication": 6.763788700699805 }, "n": 84 }, "3": { "components_ms": { "attention": 5.200173051023209, "dense_mlp_compute": 0.1775682560000001, "ep_communication": 6.661276281625032, "moe_compute": 5.007192220974576, "moe_routing": 1.473557161193642, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 20.49739246687946, "tp_dp_communication": 6.661276281625032 }, "n": 31 }, "4": { "components_ms": { "attention": 5.382115157103207, "dense_mlp_compute": 0.17756825600000006, "ep_communication": 6.661276281625032, "moe_compute": 5.007192220974576, "moe_routing": 1.473557161193642, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 20.679334572560467, "tp_dp_communication": 6.661276281625032 }, "n": 30 }, "5": { "components_ms": { "attention": 5.415451423636545, "dense_mlp_compute": 0.1794693120000007, "ep_communication": 6.619871115982532, "moe_compute": 8.776293513593586, "moe_routing": 1.5424181980825344, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 26.207872972272465, "tp_dp_communication": 6.619871115982532 }, "n": 27 }, "6": { "components_ms": { "attention": 5.4587636156365456, "dense_mlp_compute": 0.1794693120000007, "ep_communication": 6.619871115982532, "moe_compute": 8.776293513593586, "moe_routing": 1.5424181980825342, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 26.251185164551355, "tp_dp_communication": 6.619871115982532 }, "n": 26 }, "7": { "components_ms": { "attention": 5.8131280821460445, "dense_mlp_compute": 0.1794693120000007, "ep_communication": 6.619871115982532, "moe_compute": 8.776293513593586, "moe_routing": 1.5424181980825344, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 26.60554963096574, "tp_dp_communication": 6.619871115982532 }, "n": 26 }, "8": { "components_ms": { "attention": 5.8131280821460445, "dense_mlp_compute": 0.1794693120000007, "ep_communication": 6.619871115982532, "moe_compute": 8.776293513593586, "moe_routing": 1.5424181980825347, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 26.60554963097006, "tp_dp_communication": 6.619871115982532 }, "n": 27 }, "9": { "components_ms": { "attention": 5.8728644721904795, "dense_mlp_compute": 0.18060032000000073, "ep_communication": 6.824791048020123, "moe_compute": 10.391190702777715, "moe_routing": 1.5681029842793537, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 37.672915049639535, "tp_dp_communication": 6.824791048020123 }, "n": 21 } }, "component_source": "op_trace_execution_time_override", "decode_batch_size": { "cv": 0.3602756967919564, "distinct_n": 24, "max": 24.0, "mean": 18.93782383419689, "min": 1.0, "n": 1737 }, "decode_bearing_rows": 1737, "decode_token_weighted_all_step_components_ms": { "attention": 6.38060442207261, "dense_mlp_compute": 0.16958377884622666, "ep_communication": 6.235402017662346, "moe_compute": 13.024343946852467, "moe_routing": 1.5161854734738416, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 54.156672699566656, "tp_dp_communication": 6.235402017662346 }, "decode_token_weighted_mixed_step_share": 0.08077215382276942, "mixed_prefill_decode_rows": 128, "pure_decode_rows": 1609, "pure_decode_token_weighted_components_ms": { "attention": 6.853695012970485, "dense_mlp_compute": 0.1824026696707446, "ep_communication": 6.765971286395407, "moe_compute": 14.092651702097841, "moe_routing": 1.638092363428458, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 38.94606316261678, "tp_dp_communication": 6.765971286395407 }, "scorer_equivalence": { "base_metrics": { "e2e_mean_ms": 14056.464119438264, "e2e_p50_ms": 14650.653983203298, "e2e_p90_ms": 14674.997135818061, "e2e_p95_ms": 14677.859760866291, "slos": { "tpot_100ms": { "feasible": true, "pass_rate": 1.0, "passed": 129 }, "tpot_150ms": { "feasible": true, "pass_rate": 1.0, "passed": 129 }, "tpot_180ms": { "feasible": true, "pass_rate": 1.0, "passed": 129 }, "tpot_50ms": { "feasible": false, "pass_rate": 0.14728682170542637, "passed": 19 } }, "tpot_mean_ms": 54.15667269956665, "tpot_p50_ms": 56.52350191837838, "tpot_p90_ms": 56.52350850045728, "tpot_p95_ms": 56.523546100039816, "ttft_mean_ms": 246.51258104876885, "ttft_p50_ms": 246.7781280760306, "ttft_p90_ms": 263.0087113349084, "ttft_p95_ms": 264.77576248352364 }, "request_metrics_byte_identical": true, "request_metrics_sha256": "51a848c4c12eacabbc72a0f6a8b5c1863e8b624b316b7ab55341e3fe5a3a753b" }, "stage_rows": 1738, "trace_validation": { "diagnostic_wait_ms": { "cv": 0.3169483933455645, "distinct_n": 26, "max": 67.2823542576566, "mean": 38.03960569005978, "min": 7.116029381293295, "n": 1609 }, "event_names": { "attn_decode": 1737, "attn_kv_cache_save": 1738, "attn_post_proj": 1738, "attn_pre_proj": 1738, "attn_prefill": 129, "attn_rope": 1738, "attn_tensor_parallel_allreduce": 1738, "expert_parallel_allreduce": 1738, "expert_parallel_allreduce_wait": 1609, "input_layernorm": 1738, "moe_gating_linear": 1738, "moe_gating_routing_topk": 1738, "moe_grouped_gemm": 1738, "moe_shuffling": 1738, "post_attention_layernorm": 1738 }, "ledger_batches": 1738, "serialized_component_sum_over_stage_span": { "cv": 0.30467075878025907, "distinct_n": 69, "max": 1.4091742542979306, "mean": 0.8931198465670052, "min": 0.010604399884068217, "n": 1738 }, "trace_batches": 1738, "trace_path": "/home/admin/cpfs/wjh/aituner/qwen235-fixed-pd-state-diagnosis-20260719-r1/frontier-optrace/tp8_ep8_mns64/frontier_metrics/qwen3_235b_a22b/online_serving/qwen235_fixed_pd_state_tp8_ep8_mns64/op_traces.jsonl" } } }, "simulator_internal_all_step_tp8_minus_tp4_ms": { "attention": -7.461942625219683, "dense_mlp_compute": -0.12314137296116046, "ep_communication": 6.235402017662346, "moe_compute": -32.45444243169211, "moe_routing": -0.2861742505642797, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -20.06625468177714, "tp_dp_communication": -6.571107062807271 }, "status": "PASS", "verdict": "Exact real state composition flips Frontier to the correct TP4 winner; the ranking error is caused by closed-loop state/composition mismatch, not a conditional stage reversal." }