{ "contract": { "component_time": "sum of CUDA kernel durations inside execute range", "timing": "CUDA graph-on GPU execute annotations", "tp_aggregation": "per-rank; slowest rank mean approximates critical path" }, "label": "tp4-b4-r1", "rank_summary": { "component_rank_mean_ms": { "attention": 0.8023426607142858, "collective": 0.5361581428571428, "linear_norm_rope": 0.8392915178571427, "moe": 1.9595749285714295, "other": 0.021800214285714284, "output_head": 0.04583946428571428, "router": 0.1894944999999999 }, "ranks": 4, "slowest_rank_execute_mean_ms": 4.516427428571428, "slowest_rank_kernel_busy_mean_ms": 4.397215785714287 }, "ranks": [ { "components": { "attention": { "mean_ms": 0.8026924285714286, "n": 14, "p50_ms": 0.8022965, "p95_ms": 0.810657, "population_std_ms": 0.004568636975764919 }, "collective": { "mean_ms": 0.5177565714285713, "n": 14, "p50_ms": 0.5184174999999998, "p95_ms": 0.5240059999999997, "population_std_ms": 0.0039342607349554136 }, "linear_norm_rope": { "mean_ms": 0.8483352857142855, "n": 14, "p50_ms": 0.8486384999999999, "p95_ms": 0.8519969999999999, "population_std_ms": 0.0017219747562680734 }, "moe": { "mean_ms": 1.9629181428571427, "n": 14, "p50_ms": 1.9689039999999998, "p95_ms": 2.131421, "population_std_ms": 0.11758295795361873 }, "other": { "mean_ms": 0.022141571428571427, "n": 14, "p50_ms": 0.022127, "p95_ms": 0.022622999999999997, "population_std_ms": 0.00024374275499436835 }, "output_head": { "mean_ms": 0.045906214285714286, "n": 14, "p50_ms": 0.045871999999999996, "p95_ms": 0.046592, "population_std_ms": 0.00048383456124285047 }, "router": { "mean_ms": 0.18891014285714272, "n": 14, "p50_ms": 0.18883199999999986, "p95_ms": 0.18931099999999992, "population_std_ms": 0.00019712608624317712 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_1(1)": 1, "execute_context_0(0)_generation_4(4)": 14, "execute_context_3(6144)_generation_1(1)": 1 }, "execute_wall": { "mean_ms": 4.515594, "n": 14, "p50_ms": 4.512055999999999, "p95_ms": 4.8260879999999995, "population_std_ms": 0.14829775976248402 }, "gpu_kernel_busy": { "mean_ms": 4.388660357142856, "n": 14, "p50_ms": 4.3929335, "p95_ms": 4.560478, "population_std_ms": 0.12189088321563175 }, "non_kernel_gap": { "mean_ms": 0.12693364285714326, "n": 14, "p50_ms": 0.10895650000000145, "p95_ms": 0.3681599999999996, "population_std_ms": 0.06698859556415654 }, "selected_execute_annotation": "execute_context_0(0)_generation_4(4)", "steps": 14, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b4-r1-20260723-20260723T091059346688Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b4-r1/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784798099190414139.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.7969025714285717, "n": 14, "p50_ms": 0.7975640000000002, "p95_ms": 0.803777, "population_std_ms": 0.004672418671833448 }, "collective": { "mean_ms": 0.5435259285714286, "n": 14, "p50_ms": 0.5245414999999998, "p95_ms": 0.7792909999999997, "population_std_ms": 0.0654428389790491 }, "linear_norm_rope": { "mean_ms": 0.8351954285714284, "n": 14, "p50_ms": 0.8352339999999999, "p95_ms": 0.8379900000000003, "population_std_ms": 0.0011727439566058622 }, "moe": { "mean_ms": 1.9629085714285726, "n": 14, "p50_ms": 1.9686130000000002, "p95_ms": 2.1275570000000004, "population_std_ms": 0.11811909377144619 }, "other": { "mean_ms": 0.02171192857142857, "n": 14, "p50_ms": 0.021582999999999998, "p95_ms": 0.023136000000000004, "population_std_ms": 0.0004568249843501685 }, "output_head": { "mean_ms": 0.04598635714285714, "n": 14, "p50_ms": 0.0461605, "p95_ms": 0.046688, "population_std_ms": 0.00048825660805167076 }, "router": { "mean_ms": 0.18940242857142844, "n": 14, "p50_ms": 0.18939349999999988, "p95_ms": 0.19011299999999992, "population_std_ms": 0.0003183344409996063 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_1(1)": 1, "execute_context_0(0)_generation_4(4)": 14, "execute_context_3(6144)_generation_1(1)": 1 }, "execute_wall": { "mean_ms": 4.515569785714286, "n": 14, "p50_ms": 4.509453000000001, "p95_ms": 4.822798, "population_std_ms": 0.1475542723441973 }, "gpu_kernel_busy": { "mean_ms": 4.3956332142857155, "n": 14, "p50_ms": 4.3885055, "p95_ms": 4.704691000000001, "population_std_ms": 0.1480161569835144 }, "non_kernel_gap": { "mean_ms": 0.11993657142857048, "n": 14, "p50_ms": 0.12018349999999911, "p95_ms": 0.12278300000000009, "population_std_ms": 0.0023027362206822326 }, "selected_execute_annotation": "execute_context_0(0)_generation_4(4)", "steps": 14, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b4-r1-20260723-20260723T091059346688Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b4-r1/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784798099190728578.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.8076340714285717, "n": 14, "p50_ms": 0.8078890000000003, "p95_ms": 0.811872, "population_std_ms": 0.003509697513711885 }, "collective": { "mean_ms": 0.538438357142857, "n": 14, "p50_ms": 0.5197394999999998, "p95_ms": 0.7775990000000002, "population_std_ms": 0.06647859896624862 }, "linear_norm_rope": { "mean_ms": 0.8366736428571427, "n": 14, "p50_ms": 0.8371874999999998, "p95_ms": 0.8391049999999995, "population_std_ms": 0.002070122274067762 }, "moe": { "mean_ms": 1.9572025000000013, "n": 14, "p50_ms": 1.9622045000000017, "p95_ms": 2.1186610000000012, "population_std_ms": 0.11785303854665174 }, "other": { "mean_ms": 0.021651357142857146, "n": 14, "p50_ms": 0.0216015, "p95_ms": 0.022528000000000003, "population_std_ms": 0.0003619630224095226 }, "output_head": { "mean_ms": 0.04572821428571428, "n": 14, "p50_ms": 0.045616000000000004, "p95_ms": 0.046816, "population_std_ms": 0.0004743333936877599 }, "router": { "mean_ms": 0.18988764285714277, "n": 14, "p50_ms": 0.1899184999999999, "p95_ms": 0.1904639999999999, "population_std_ms": 0.00036004535570296044 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_1(1)": 1, "execute_context_0(0)_generation_4(4)": 14, "execute_context_3(6144)_generation_1(1)": 1 }, "execute_wall": { "mean_ms": 4.516208928571428, "n": 14, "p50_ms": 4.5094615000000005, "p95_ms": 4.827749, "population_std_ms": 0.14783990641591432 }, "gpu_kernel_busy": { "mean_ms": 4.397215785714287, "n": 14, "p50_ms": 4.391749500000001, "p95_ms": 4.706615000000002, "population_std_ms": 0.14841367943313954 }, "non_kernel_gap": { "mean_ms": 0.11899314285714155, "n": 14, "p50_ms": 0.11911499999999897, "p95_ms": 0.12231999999999754, "population_std_ms": 0.0022138607149742996 }, "selected_execute_annotation": "execute_context_0(0)_generation_4(4)", "steps": 14, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b4-r1-20260723-20260723T091059346688Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b4-r1/traces/profile/dp0_pp0_tp2_dcp0_ep2_rank2.1784798099190414025.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.8021415714285716, "n": 14, "p50_ms": 0.8019065000000002, "p95_ms": 0.8102380000000002, "population_std_ms": 0.004568393789542204 }, "collective": { "mean_ms": 0.5449117142857143, "n": 14, "p50_ms": 0.5278735, "p95_ms": 0.781215, "population_std_ms": 0.0655966698484312 }, "linear_norm_rope": { "mean_ms": 0.8369617142857141, "n": 14, "p50_ms": 0.8372430000000001, "p95_ms": 0.8394259999999998, "population_std_ms": 0.0013668606590375937 }, "moe": { "mean_ms": 1.9552705000000008, "n": 14, "p50_ms": 1.9632605, "p95_ms": 2.1177540000000006, "population_std_ms": 0.11724808995809416 }, "other": { "mean_ms": 0.021696, "n": 14, "p50_ms": 0.021648, "p95_ms": 0.02288, "population_std_ms": 0.0004689002330682176 }, "output_head": { "mean_ms": 0.045737071428571426, "n": 14, "p50_ms": 0.0457755, "p95_ms": 0.046496, "population_std_ms": 0.00039792039122807263 }, "router": { "mean_ms": 0.18977778571428564, "n": 14, "p50_ms": 0.1896624999999999, "p95_ms": 0.1909739999999999, "population_std_ms": 0.00041644501927821606 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_1(1)": 1, "execute_context_0(0)_generation_4(4)": 14, "execute_context_3(6144)_generation_1(1)": 1 }, "execute_wall": { "mean_ms": 4.516427428571428, "n": 14, "p50_ms": 4.508496, "p95_ms": 4.82816, "population_std_ms": 0.14821148953231575 }, "gpu_kernel_busy": { "mean_ms": 4.3964963571428575, "n": 14, "p50_ms": 4.3874035, "p95_ms": 4.705174, "population_std_ms": 0.14715990628788167 }, "non_kernel_gap": { "mean_ms": 0.11993107142857092, "n": 14, "p50_ms": 0.11941749999999951, "p95_ms": 0.1248560000000003, "population_std_ms": 0.002664138817283219 }, "selected_execute_annotation": "execute_context_0(0)_generation_4(4)", "steps": 14, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b4-r1-20260723-20260723T091059346688Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b4-r1/traces/profile/dp0_pp0_tp3_dcp0_ep3_rank3.1784798099191829059.pt.trace.json.gz" } ], "schema": "frontier-decode-batch-trace.v1" }