{ "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-b8-r2", "rank_summary": { "component_rank_mean_ms": { "attention": 0.9134566730769228, "collective": 0.5546497884615385, "linear_norm_rope": 0.8387807692307689, "moe": 2.0065153269230764, "other": 0.02364873076923077, "output_head": 0.04593917307692308, "router": 0.19024988461538456 }, "ranks": 4, "slowest_rank_execute_mean_ms": 5.046865153846154, "slowest_rank_kernel_busy_mean_ms": 4.576482615384614 }, "ranks": [ { "components": { "attention": { "mean_ms": 0.9168304615384618, "n": 13, "p50_ms": 0.9167360000000001, "p95_ms": 0.9226820000000003, "population_std_ms": 0.0042293902200123395 }, "collective": { "mean_ms": 0.533513923076923, "n": 13, "p50_ms": 0.5343079999999998, "p95_ms": 0.5469470000000001, "population_std_ms": 0.005929160823506614 }, "linear_norm_rope": { "mean_ms": 0.8429445384615385, "n": 13, "p50_ms": 0.8424360000000001, "p95_ms": 0.8458869999999998, "population_std_ms": 0.001745678030732511 }, "moe": { "mean_ms": 2.013382153846152, "n": 13, "p50_ms": 1.9625909999999984, "p95_ms": 2.195520999999998, "population_std_ms": 0.13058695301059595 }, "other": { "mean_ms": 0.023465076923076922, "n": 13, "p50_ms": 0.023581, "p95_ms": 0.023903, "population_std_ms": 0.00026946969618078375 }, "output_head": { "mean_ms": 0.045974307692307696, "n": 13, "p50_ms": 0.046048, "p95_ms": 0.046624000000000006, "population_std_ms": 0.00041656145259371096 }, "router": { "mean_ms": 0.2003721538461538, "n": 13, "p50_ms": 0.199709, "p95_ms": 0.20480099999999998, "population_std_ms": 0.002108014079873938 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_8(8)": 13, "execute_context_1(4)_generation_7(7)": 1, "execute_context_3(6144)_generation_1(1)": 1, "execute_context_4(8188)_generation_4(4)": 1 }, "execute_wall": { "mean_ms": 5.04529823076923, "n": 13, "p50_ms": 4.9983770000000005, "p95_ms": 5.2427600000000005, "population_std_ms": 0.1337420429024321 }, "gpu_kernel_busy": { "mean_ms": 4.576482615384614, "n": 13, "p50_ms": 4.520321999999998, "p95_ms": 4.770687999999998, "population_std_ms": 0.13507694537418738 }, "non_kernel_gap": { "mean_ms": 0.46881561538461686, "n": 13, "p50_ms": 0.46984200000000076, "p95_ms": 0.4780550000000021, "population_std_ms": 0.004066459044397948 }, "selected_execute_annotation": "execute_context_0(0)_generation_8(8)", "steps": 13, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b8-r2-20260723-20260723T093027863838Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b8-r2/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784799265976107810.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.9115253076923072, "n": 13, "p50_ms": 0.9091299999999993, "p95_ms": 0.9181569999999997, "population_std_ms": 0.004755129738335539 }, "collective": { "mean_ms": 0.5619680769230769, "n": 13, "p50_ms": 0.5602239999999999, "p95_ms": 0.5761279999999999, "population_std_ms": 0.0068347860634070876 }, "linear_norm_rope": { "mean_ms": 0.8369866923076922, "n": 13, "p50_ms": 0.8367649999999999, "p95_ms": 0.8395509999999997, "population_std_ms": 0.0014106170163667622 }, "moe": { "mean_ms": 2.008448384615385, "n": 13, "p50_ms": 1.955683, "p95_ms": 2.194793000000001, "population_std_ms": 0.13403461779448436 }, "other": { "mean_ms": 0.023700230769230772, "n": 13, "p50_ms": 0.023742999999999997, "p95_ms": 0.024096, "population_std_ms": 0.00023815901405643158 }, "output_head": { "mean_ms": 0.045964538461538466, "n": 13, "p50_ms": 0.045856, "p95_ms": 0.046624000000000006, "population_std_ms": 0.0003695759764471495 }, "router": { "mean_ms": 0.1853764615384615, "n": 13, "p50_ms": 0.18530699999999997, "p95_ms": 0.18560199999999993, "population_std_ms": 0.0001339481044082144 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_8(8)": 13, "execute_context_1(4)_generation_7(7)": 1, "execute_context_3(6144)_generation_1(1)": 1, "execute_context_4(8188)_generation_4(4)": 1 }, "execute_wall": { "mean_ms": 5.045370692307693, "n": 13, "p50_ms": 4.998862, "p95_ms": 5.242511, "population_std_ms": 0.13589867228614172 }, "gpu_kernel_busy": { "mean_ms": 4.573969692307692, "n": 13, "p50_ms": 4.520643, "p95_ms": 4.767782, "population_std_ms": 0.13563036850452942 }, "non_kernel_gap": { "mean_ms": 0.47140100000000024, "n": 13, "p50_ms": 0.4708439999999987, "p95_ms": 0.48116299999999956, "population_std_ms": 0.0040546694639067024 }, "selected_execute_annotation": "execute_context_0(0)_generation_8(8)", "steps": 13, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b8-r2-20260723-20260723T093027863838Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b8-r2/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784799265964743771.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.9081704615384611, "n": 13, "p50_ms": 0.9067839999999995, "p95_ms": 0.9137029999999994, "population_std_ms": 0.003844601502114216 }, "collective": { "mean_ms": 0.5607229230769231, "n": 13, "p50_ms": 0.5606410000000001, "p95_ms": 0.5753579999999999, "population_std_ms": 0.005889349049330662 }, "linear_norm_rope": { "mean_ms": 0.8375191538461533, "n": 13, "p50_ms": 0.8377699999999999, "p95_ms": 0.8382449999999991, "population_std_ms": 0.0007602619838080075 }, "moe": { "mean_ms": 2.0034716923076927, "n": 13, "p50_ms": 1.9509769999999995, "p95_ms": 2.1876420000000003, "population_std_ms": 0.1321404819107208 }, "other": { "mean_ms": 0.023784923076923075, "n": 13, "p50_ms": 0.023744, "p95_ms": 0.024192, "population_std_ms": 0.00026262885820062297 }, "output_head": { "mean_ms": 0.04589046153846154, "n": 13, "p50_ms": 0.04592, "p95_ms": 0.046464, "population_std_ms": 0.0003319519463334356 }, "router": { "mean_ms": 0.18966023076923072, "n": 13, "p50_ms": 0.18950599999999995, "p95_ms": 0.19261299999999995, "population_std_ms": 0.0014891042818184978 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_8(8)": 13, "execute_context_1(4)_generation_7(7)": 1, "execute_context_3(6144)_generation_1(1)": 1, "execute_context_4(8188)_generation_4(4)": 1 }, "execute_wall": { "mean_ms": 5.043654153846154, "n": 13, "p50_ms": 4.99831, "p95_ms": 5.233926, "population_std_ms": 0.1368864811675641 }, "gpu_kernel_busy": { "mean_ms": 4.569219846153846, "n": 13, "p50_ms": 4.526768999999998, "p95_ms": 4.755531999999999, "population_std_ms": 0.13605665130991768 }, "non_kernel_gap": { "mean_ms": 0.47443430769230827, "n": 13, "p50_ms": 0.47430400000000006, "p95_ms": 0.48320900000000044, "population_std_ms": 0.0038414357969708507 }, "selected_execute_annotation": "execute_context_0(0)_generation_8(8)", "steps": 13, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b8-r2-20260723-20260723T093027863838Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b8-r2/traces/profile/dp0_pp0_tp2_dcp0_ep2_rank2.1784799265970389602.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.9173004615384611, "n": 13, "p50_ms": 0.915619999999999, "p95_ms": 0.9253379999999995, "population_std_ms": 0.0052849307922895015 }, "collective": { "mean_ms": 0.5623942307692308, "n": 13, "p50_ms": 0.5634610000000001, "p95_ms": 0.570651, "population_std_ms": 0.006084772534195447 }, "linear_norm_rope": { "mean_ms": 0.8376726923076918, "n": 13, "p50_ms": 0.8376949999999989, "p95_ms": 0.8402979999999994, "population_std_ms": 0.0016093297880994772 }, "moe": { "mean_ms": 2.000759076923077, "n": 13, "p50_ms": 1.9501820000000014, "p95_ms": 2.184468999999999, "population_std_ms": 0.12953482671732042 }, "other": { "mean_ms": 0.023644692307692308, "n": 13, "p50_ms": 0.023615999999999998, "p95_ms": 0.023968, "population_std_ms": 0.0002102991951465574 }, "output_head": { "mean_ms": 0.04592738461538462, "n": 13, "p50_ms": 0.045824, "p95_ms": 0.046688, "population_std_ms": 0.0003889230769230783 }, "router": { "mean_ms": 0.18559069230769226, "n": 13, "p50_ms": 0.18560099999999996, "p95_ms": 0.18578999999999996, "population_std_ms": 0.00010438640098240813 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_8(8)": 13, "execute_context_1(4)_generation_7(7)": 1, "execute_context_3(6144)_generation_1(1)": 1, "execute_context_4(8188)_generation_4(4)": 1 }, "execute_wall": { "mean_ms": 5.046865153846154, "n": 13, "p50_ms": 5.003904, "p95_ms": 5.240352, "population_std_ms": 0.1362175904832164 }, "gpu_kernel_busy": { "mean_ms": 4.57328923076923, "n": 13, "p50_ms": 4.526548000000001, "p95_ms": 4.767014999999998, "population_std_ms": 0.13627994044452013 }, "non_kernel_gap": { "mean_ms": 0.47357592307692375, "n": 13, "p50_ms": 0.474012000000001, "p95_ms": 0.4803690000000005, "population_std_ms": 0.0037547593482557514 }, "selected_execute_annotation": "execute_context_0(0)_generation_8(8)", "steps": 13, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b8-r2-20260723-20260723T093027863838Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b8-r2/traces/profile/dp0_pp0_tp3_dcp0_ep3_rank3.1784799265964152963.pt.trace.json.gz" } ], "schema": "frontier-decode-batch-trace.v1" }