{ "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": 46.414892969, "tp_dp_communication": 12.225778813333333 }, "coverage": 1.0, "supported_samples": 45, "total_samples": 45, "unsupported": {} }, "tp8_ep8_mns64": { "components_ms": { "attention": 0.06450142600000001, "dense_mlp_compute": 0.00192128, "ep_communication": 0.07260416, "moe_compute": 0.110544582, "moe_routing": 0.016681946999999996, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.338857555, "tp_dp_communication": 0.07260416 }, "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": -6.239321134333333, "dense_mlp_compute": -0.17691434666666667, "ep_communication": 0.07260416, "moe_compute": -26.338732636333333, "moe_routing": -1.2404968033333332, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -46.076035414, "tp_dp_communication": -12.153174653333334 } }, "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 } } ] } }, "reference": { "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": -5.865362041999999, "dense_mlp_compute": -0.17567923200000002, "ep_communication": 0.0812872, "moe_compute": -4.2460797470000005, "moe_routing": -1.218856335, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -25.770368131999998, "tp_dp_communication": -14.345677976 }, "tp8_n": 34 }, "10": { "tp4_n": 38, "tp8_minus_tp4_ms": { "attention": -6.732672957, "dense_mlp_compute": -0.17867904, "ep_communication": 0.07260416, "moe_compute": -41.060828877, "moe_routing": -1.28066121, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -60.641066124000005, "tp_dp_communication": -11.460828200000002 }, "tp8_n": 22 }, "11": { "tp4_n": 42, "tp8_minus_tp4_ms": { "attention": -6.7796566579999995, "dense_mlp_compute": -0.17867904, "ep_communication": 0.07260415999999999, "moe_compute": -41.060828877, "moe_routing": -1.28066121, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -60.68804982500001, "tp_dp_communication": -11.460828200000002 }, "tp8_n": 22 }, "12": { "tp4_n": 46, "tp8_minus_tp4_ms": { "attention": -6.779656658, "dense_mlp_compute": -0.17867904, "ep_communication": 0.07260416, "moe_compute": -41.060828877, "moe_routing": -1.28066121, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -60.68804982500001, "tp_dp_communication": -11.460828200000002 }, "tp8_n": 21 }, "13": { "tp4_n": 46, "tp8_minus_tp4_ms": { "attention": -7.2421678100000015, "dense_mlp_compute": -0.17867903999999998, "ep_communication": 0.07260416, "moe_compute": -41.06082887699999, "moe_routing": -1.28066121, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -61.150560977, "tp_dp_communication": -11.460828200000002 }, "tp8_n": 22 }, "14": { "tp4_n": 47, "tp8_minus_tp4_ms": { "attention": -7.248219534, "dense_mlp_compute": -0.17867904000000004, "ep_communication": 0.07260416, "moe_compute": -41.060828877, "moe_routing": -1.28066121, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -61.156612701, "tp_dp_communication": -11.460828200000002 }, "tp8_n": 21 }, "15": { "tp4_n": 663, "tp8_minus_tp4_ms": { "attention": -7.264528133999999, "dense_mlp_compute": -0.17867904000000004, "ep_communication": 0.07260416, "moe_compute": -41.060828877, "moe_routing": -1.28066121, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -61.172921300999995, "tp_dp_communication": -11.4608282 }, "tp8_n": 21 }, "16": { "tp4_n": 1053, "tp8_minus_tp4_ms": { "attention": -7.264528134, "dense_mlp_compute": -0.17867904, "ep_communication": 0.07260416, "moe_compute": -41.060828877, "moe_routing": -1.28066121, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -61.172921301, "tp_dp_communication": -11.460828200000002 }, "tp8_n": 22 }, "2": { "tp4_n": 52, "tp8_minus_tp4_ms": { "attention": -5.993161589230768, "dense_mlp_compute": -0.17567923200000002, "ep_communication": 0.07627888, "moe_compute": -5.365670131, "moe_routing": -1.222289295, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -26.05095133323077, "tp_dp_communication": -13.370429966 }, "tp8_n": 32 }, "3": { "tp4_n": 47, "tp8_minus_tp4_ms": { "attention": -6.04432608180851, "dense_mlp_compute": -0.17567923200000002, "ep_communication": 0.070864641, "moe_compute": -9.925579423, "moe_routing": -1.2278096929999998, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -29.95224206780851, "tp_dp_communication": -12.649712279 }, "tp8_n": 31 }, "4": { "tp4_n": 48, "tp8_minus_tp4_ms": { "attention": -6.228110533, "dense_mlp_compute": -0.17567923200000002, "ep_communication": 0.070864641, "moe_compute": -9.925579423, "moe_routing": -1.227809693, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -30.136026518999998, "tp_dp_communication": -12.649712279 }, "tp8_n": 30 }, "5": { "tp4_n": 34, "tp8_minus_tp4_ms": { "attention": -6.255439117, "dense_mlp_compute": -0.17756006399999996, "ep_communication": 0.070424161, "moe_compute": -34.591127289999996, "moe_routing": -1.247616504, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -54.109274413, "tp_dp_communication": -11.907955599 }, "tp8_n": 27 }, "6": { "tp4_n": 33, "tp8_minus_tp4_ms": { "attention": -6.298408004000001, "dense_mlp_compute": -0.177560064, "ep_communication": 0.07042416100000001, "moe_compute": -34.591127289999996, "moe_routing": -1.247616504, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -54.152243299999995, "tp_dp_communication": -11.907955599 }, "tp8_n": 26 }, "7": { "tp4_n": 34, "tp8_minus_tp4_ms": { "attention": -6.6722336250000005, "dense_mlp_compute": -0.177560064, "ep_communication": 0.070424161, "moe_compute": -34.59112728999999, "moe_routing": -1.247616504, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -54.52606892099999, "tp_dp_communication": -11.907955599 }, "tp8_n": 26 }, "8": { "tp4_n": 33, "tp8_minus_tp4_ms": { "attention": -6.6722336250000005, "dense_mlp_compute": -0.177560064, "ep_communication": 0.070424161, "moe_compute": -34.591127289999996, "moe_routing": -1.247616504, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -54.526068921, "tp_dp_communication": -11.907955599 }, "tp8_n": 27 }, "9": { "tp4_n": 32, "tp8_minus_tp4_ms": { "attention": -6.720033763, "dense_mlp_compute": -0.17867904, "ep_communication": 0.07260416, "moe_compute": -41.060828877, "moe_routing": -1.28066121, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -60.62842693, "tp_dp_communication": -11.460828200000002 }, "tp8_n": 21 } }, "schema": "qwen235-fixed-pd-state-diagnosis-v1", "scope": { "graph_observability": "Frontier ledger exposes additive execution components but no direct graph bucket/padding/launch-overhead field; graph effects remain folded into predictors", "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": 26.035006492999997, "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": 60.978072014000006, "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": 61.025546676000005, "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": 61.025546676000005, "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": 61.492820292, "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": 61.498934954, "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": 61.515411951, "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": 61.515411951000004, "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": 26.30688845523077, "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": 30.220125505808507, "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": 30.405845511, "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": 54.419416698, "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": 54.462846352999996, "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": 54.84044180899999, "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": 54.840441809, "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": 60.96526034, "tp_dp_communication": 11.53343236 }, "n": 32 } }, "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": 74.222927382152, "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": 60.782085996374114, "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 }, "tp8_ep8_mns64": { "batch_support": { "1": { "components_ms": { "attention": 0.053460434, "dense_mlp_compute": 0.0018890240000000002, "ep_communication": 0.0812872, "moe_compute": 0.030952589000000003, "moe_routing": 0.015761914, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.264638361, "tp_dp_communication": 0.0812872 }, "n": 34 }, "10": { "components_ms": { "attention": 0.062649761, "dense_mlp_compute": 0.0019212800000000003, "ep_communication": 0.07260416, "moe_compute": 0.11054458199999999, "moe_routing": 0.016681947, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.33700589, "tp_dp_communication": 0.07260416 }, "n": 22 }, "11": { "components_ms": { "attention": 0.063140722, "dense_mlp_compute": 0.00192128, "ep_communication": 0.07260415999999999, "moe_compute": 0.11054458200000002, "moe_routing": 0.016681947, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.337496851, "tp_dp_communication": 0.07260415999999999 }, "n": 22 }, "12": { "components_ms": { "attention": 0.06314072200000001, "dense_mlp_compute": 0.00192128, "ep_communication": 0.07260416, "moe_compute": 0.110544582, "moe_routing": 0.016681946999999996, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.337496851, "tp_dp_communication": 0.07260416 }, "n": 21 }, "13": { "components_ms": { "attention": 0.067903186, "dense_mlp_compute": 0.00192128, "ep_communication": 0.07260416, "moe_compute": 0.110544582, "moe_routing": 0.016681946999999996, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.342259315, "tp_dp_communication": 0.07260416 }, "n": 22 }, "14": { "components_ms": { "attention": 0.067966124, "dense_mlp_compute": 0.0019212799999999998, "ep_communication": 0.07260416, "moe_compute": 0.110544582, "moe_routing": 0.016681947, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.342322253, "tp_dp_communication": 0.07260416 }, "n": 21 }, "15": { "components_ms": { "attention": 0.068134521, "dense_mlp_compute": 0.0019212799999999998, "ep_communication": 0.07260416, "moe_compute": 0.11054458200000002, "moe_routing": 0.016681947, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.34249065, "tp_dp_communication": 0.07260416 }, "n": 21 }, "16": { "components_ms": { "attention": 0.068134521, "dense_mlp_compute": 0.00192128, "ep_communication": 0.07260416, "moe_compute": 0.110544582, "moe_routing": 0.016681947, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.34249065, "tp_dp_communication": 0.07260416 }, "n": 22 }, "17": { "components_ms": { "attention": 0.070769479, "dense_mlp_compute": 0.0019433600000000003, "ep_communication": 0.071955199, "moe_compute": 0.15567622299999997, "moe_routing": 0.017531437, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.38983089699999995, "tp_dp_communication": 0.071955199 }, "n": 31 }, "18": { "components_ms": { "attention": 0.07076947899999998, "dense_mlp_compute": 0.00194336, "ep_communication": 0.071955199, "moe_compute": 0.155676223, "moe_routing": 0.017531437, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.38983089699999995, "tp_dp_communication": 0.071955199 }, "n": 30 }, "19": { "components_ms": { "attention": 0.070769479, "dense_mlp_compute": 0.0019433599999999999, "ep_communication": 0.071955199, "moe_compute": 0.155676223, "moe_routing": 0.017531437, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.389830897, "tp_dp_communication": 0.071955199 }, "n": 32 }, "2": { "components_ms": { "attention": 0.054839835, "dense_mlp_compute": 0.001889024, "ep_communication": 0.07627888, "moe_compute": 0.030952589, "moe_routing": 0.015697914, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.255937122, "tp_dp_communication": 0.07627888 }, "n": 32 }, "20": { "components_ms": { "attention": 0.070769479, "dense_mlp_compute": 0.0019433600000000003, "ep_communication": 0.071955199, "moe_compute": 0.15567622299999997, "moe_routing": 0.017531437, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.38983089699999995, "tp_dp_communication": 0.071955199 }, "n": 33 }, "21": { "components_ms": { "attention": 0.074295324, "dense_mlp_compute": 0.00194336, "ep_communication": 0.071955199, "moe_compute": 0.155676223, "moe_routing": 0.017531437, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.393356742, "tp_dp_communication": 0.071955199 }, "n": 37 }, "22": { "components_ms": { "attention": 0.074295324, "dense_mlp_compute": 0.00194336, "ep_communication": 0.07195519899999998, "moe_compute": 0.155676223, "moe_routing": 0.017531437, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.393356742, "tp_dp_communication": 0.07195519899999998 }, "n": 51 }, "23": { "components_ms": { "attention": 0.074295324, "dense_mlp_compute": 0.0019433599999999999, "ep_communication": 0.071955199, "moe_compute": 0.155676223, "moe_routing": 0.017531437, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.393356742, "tp_dp_communication": 0.071955199 }, "n": 906 }, "24": { "components_ms": { "attention": 0.074295324, "dense_mlp_compute": 0.0019433600000000003, "ep_communication": 0.071955199, "moe_compute": 0.155676223, "moe_routing": 0.017531437, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.393356742, "tp_dp_communication": 0.071955199 }, "n": 84 }, "3": { "components_ms": { "attention": 0.05532099, "dense_mlp_compute": 0.0018890240000000002, "ep_communication": 0.070864641, "moe_compute": 0.053268002, "moe_routing": 0.015676139999999998, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.26788343800000003, "tp_dp_communication": 0.070864641 }, "n": 31 }, "4": { "components_ms": { "attention": 0.057256544, "dense_mlp_compute": 0.001889024, "ep_communication": 0.070864641, "moe_compute": 0.053268002, "moe_routing": 0.015676139999999998, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.26981899200000004, "tp_dp_communication": 0.070864641 }, "n": 30 }, "5": { "components_ms": { "attention": 0.057611185, "dense_mlp_compute": 0.001909248, "ep_communication": 0.070424161, "moe_compute": 0.09336482499999998, "moe_routing": 0.016408705, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.31014228499999996, "tp_dp_communication": 0.070424161 }, "n": 27 }, "6": { "components_ms": { "attention": 0.058071952999999996, "dense_mlp_compute": 0.001909248, "ep_communication": 0.07042416100000001, "moe_compute": 0.093364825, "moe_routing": 0.016408705, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.310603053, "tp_dp_communication": 0.07042416100000001 }, "n": 26 }, "7": { "components_ms": { "attention": 0.061841787999999995, "dense_mlp_compute": 0.001909248, "ep_communication": 0.070424161, "moe_compute": 0.093364825, "moe_routing": 0.016408705, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.314372888, "tp_dp_communication": 0.070424161 }, "n": 26 }, "8": { "components_ms": { "attention": 0.061841787999999995, "dense_mlp_compute": 0.0019092480000000003, "ep_communication": 0.070424161, "moe_compute": 0.093364825, "moe_routing": 0.016408705, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.314372888, "tp_dp_communication": 0.070424161 }, "n": 27 }, "9": { "components_ms": { "attention": 0.062477281, "dense_mlp_compute": 0.0019212800000000003, "ep_communication": 0.07260416, "moe_compute": 0.11054458199999999, "moe_routing": 0.016681947, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.33683341, "tp_dp_communication": 0.07260416 }, "n": 21 } }, "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": 0.14751953504742363, "dense_mlp_compute": 0.0036978849298677607, "ep_communication": 0.082097370873993, "moe_compute": 0.20779839324350205, "moe_routing": 0.02642429565140599, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.5496348506201855, "tp_dp_communication": 0.082097370873993 }, "decode_token_weighted_mixed_step_share": 0.08077215382276942, "mixed_prefill_decode_rows": 128, "pure_decode_rows": 1609, "pure_decode_token_weighted_components_ms": { "attention": 0.07291164903783319, "dense_mlp_compute": 0.0019404539326675046, "ep_communication": 0.07197841798710232, "moe_compute": 0.14992182626155828, "moe_routing": 0.017426514274852836, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": 0.38615727948111644, "tp_dp_communication": 0.07197841798710232 }, "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 } }, "simulator_internal_all_step_tp8_minus_tp4_ms": { "attention": -13.695027512244868, "dense_mlp_compute": -0.28902726687751934, "ep_communication": 0.082097370873993, "moe_compute": -45.270987985301076, "moe_routing": -1.7759354283867153, "pipeline_communication": 0.0, "runtime_overhead": 0.0, "total": -73.67329253153181, "tp_dp_communication": -12.724411709595623 }, "status": "PASS", "verdict": "Active-batch-count mismatch alone is insufficient: after exact reweighting to each config's real Running histogram, Frontier still predicts TP8 faster." }