{ "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": "tp2-b8-r1", "rank_summary": { "component_rank_mean_ms": { "attention": 1.4162915000000003, "collective": 0.5046254615384616, "linear_norm_rope": 0.933206192307692, "moe": 2.681186538461537, "other": 0.023443884615384616, "output_head": 0.08826711538461537, "router": 0.19981553846153838 }, "ranks": 2, "slowest_rank_execute_mean_ms": 5.967337846153845, "slowest_rank_kernel_busy_mean_ms": 5.849403615384613 }, "ranks": [ { "components": { "attention": { "mean_ms": 1.4268944615384618, "n": 13, "p50_ms": 1.4273899999999997, "p95_ms": 1.4289299999999996, "population_std_ms": 0.0013227596802130133 }, "collective": { "mean_ms": 0.4871666153846154, "n": 13, "p50_ms": 0.4847079999999998, "p95_ms": 0.5161030000000001, "population_std_ms": 0.009071831835526453 }, "linear_norm_rope": { "mean_ms": 0.9357503846153842, "n": 13, "p50_ms": 0.9351129999999993, "p95_ms": 0.9375759999999999, "population_std_ms": 0.0012191190727774577 }, "moe": { "mean_ms": 2.6808982307692295, "n": 13, "p50_ms": 2.729251, "p95_ms": 2.8241379999999983, "population_std_ms": 0.11820978926868417 }, "other": { "mean_ms": 0.023988000000000002, "n": 13, "p50_ms": 0.023935, "p95_ms": 0.024639999999999995, "population_std_ms": 0.0002731643630321658 }, "output_head": { "mean_ms": 0.08829546153846153, "n": 13, "p50_ms": 0.088256, "p95_ms": 0.08921599999999999, "population_std_ms": 0.00048060836693389233 }, "router": { "mean_ms": 0.2012756923076922, "n": 13, "p50_ms": 0.20156699999999994, "p95_ms": 0.20582599999999993, "population_std_ms": 0.0022949889352713113 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_8(8)": 13, "execute_context_1(2048)_generation_1(1)": 1, "execute_context_3(4098)_generation_5(5)": 1, "execute_context_4(8190)_generation_2(2)": 1 }, "execute_wall": { "mean_ms": 5.966980846153846, "n": 13, "p50_ms": 6.004943, "p95_ms": 6.112047, "population_std_ms": 0.11913819132925879 }, "gpu_kernel_busy": { "mean_ms": 5.844268846153844, "n": 13, "p50_ms": 5.885293999999999, "p95_ms": 5.987602999999998, "population_std_ms": 0.11849233575983938 }, "non_kernel_gap": { "mean_ms": 0.12271200000000157, "n": 13, "p50_ms": 0.12307100000000126, "p95_ms": 0.12728500000000142, "population_std_ms": 0.0027851573357023283 }, "selected_execute_annotation": "execute_context_0(0)_generation_8(8)", "steps": 13, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp2-b8-r1-20260723-20260723T091715999468Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b8-r1/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784798455024962606.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 1.405688538461539, "n": 13, "p50_ms": 1.4057520000000006, "p95_ms": 1.4114940000000005, "population_std_ms": 0.0022431369386294517 }, "collective": { "mean_ms": 0.5220843076923077, "n": 13, "p50_ms": 0.5193970000000001, "p95_ms": 0.5542680000000001, "population_std_ms": 0.010336781774023671 }, "linear_norm_rope": { "mean_ms": 0.9306619999999997, "n": 13, "p50_ms": 0.9303679999999996, "p95_ms": 0.9333509999999994, "population_std_ms": 0.0014067406955851874 }, "moe": { "mean_ms": 2.6814748461538445, "n": 13, "p50_ms": 2.7311729999999965, "p95_ms": 2.8229829999999962, "population_std_ms": 0.11917174241136594 }, "other": { "mean_ms": 0.02289976923076923, "n": 13, "p50_ms": 0.022943999999999996, "p95_ms": 0.02352, "population_std_ms": 0.0002890651121343674 }, "output_head": { "mean_ms": 0.08823876923076922, "n": 13, "p50_ms": 0.088193, "p95_ms": 0.088768, "population_std_ms": 0.0003492319383240336 }, "router": { "mean_ms": 0.19835538461538452, "n": 13, "p50_ms": 0.1982099999999999, "p95_ms": 0.2010899999999999, "population_std_ms": 0.0022037652233764197 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_8(8)": 13, "execute_context_1(2048)_generation_1(1)": 1, "execute_context_3(4098)_generation_5(5)": 1, "execute_context_4(8190)_generation_2(2)": 1 }, "execute_wall": { "mean_ms": 5.967337846153845, "n": 13, "p50_ms": 6.0104049999999996, "p95_ms": 6.1097969999999995, "population_std_ms": 0.11987574925913026 }, "gpu_kernel_busy": { "mean_ms": 5.849403615384613, "n": 13, "p50_ms": 5.889734999999996, "p95_ms": 5.993167999999996, "population_std_ms": 0.11980136802451119 }, "non_kernel_gap": { "mean_ms": 0.11793423076923243, "n": 13, "p50_ms": 0.11715500000000123, "p95_ms": 0.12245800000000262, "population_std_ms": 0.002861606035183301 }, "selected_execute_annotation": "execute_context_0(0)_generation_8(8)", "steps": 13, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp2-b8-r1-20260723-20260723T091715999468Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b8-r1/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784798455030360286.pt.trace.json.gz" } ], "schema": "frontier-decode-batch-trace.v1" }