{ "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-b2-r2", "rank_summary": { "component_rank_mean_ms": { "attention": 0.7204233125, "collective": 0.560326375, "linear_norm_rope": 0.8352021093750001, "moe": 1.7914327656249986, "other": 0.020750828125000002, "output_head": 0.04556265625, "router": 0.18667273437499995 }, "ranks": 4, "slowest_rank_execute_mean_ms": 4.6200790625, "slowest_rank_kernel_busy_mean_ms": 4.168571874999999 }, "ranks": [ { "components": { "attention": { "mean_ms": 0.7155257500000002, "n": 16, "p50_ms": 0.7066910000000002, "p95_ms": 0.7447440000000003, "population_std_ms": 0.01558176035265282 }, "collective": { "mean_ms": 0.5219253125, "n": 16, "p50_ms": 0.5189115, "p95_ms": 0.5383740000000001, "population_std_ms": 0.008178805388921035 }, "linear_norm_rope": { "mean_ms": 0.8318194374999998, "n": 16, "p50_ms": 0.8315799999999995, "p95_ms": 0.8361279999999999, "population_std_ms": 0.001956002842813193 }, "moe": { "mean_ms": 1.8462991249999985, "n": 16, "p50_ms": 1.8014489999999976, "p95_ms": 1.9688019999999977, "population_std_ms": 0.098837188149802 }, "other": { "mean_ms": 0.020839937500000003, "n": 16, "p50_ms": 0.020830500000000002, "p95_ms": 0.021311, "population_std_ms": 0.00026370875714270555 }, "output_head": { "mean_ms": 0.0455260625, "n": 16, "p50_ms": 0.045296, "p95_ms": 0.047200000000000006, "population_std_ms": 0.0005808763281402957 }, "router": { "mean_ms": 0.1866362499999999, "n": 16, "p50_ms": 0.18664149999999985, "p95_ms": 0.1869089999999999, "population_std_ms": 0.0001586574533389501 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_2(2)": 16 }, "execute_wall": { "mean_ms": 4.6200790625, "n": 16, "p50_ms": 4.560737, "p95_ms": 4.785777, "population_std_ms": 0.1217774651913628 }, "gpu_kernel_busy": { "mean_ms": 4.168571874999999, "n": 16, "p50_ms": 4.106530999999998, "p95_ms": 4.335109999999998, "population_std_ms": 0.12256936973397699 }, "non_kernel_gap": { "mean_ms": 0.4515071875000016, "n": 16, "p50_ms": 0.45221700000000054, "p95_ms": 0.4565129999999993, "population_std_ms": 0.002988645119839536 }, "selected_execute_annotation": "execute_context_0(0)_generation_2(2)", "steps": 16, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-batch-tp4-b2-r2-20260723-20260723T090307191004Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b2-r2/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784797602726202234.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.7221352500000001, "n": 16, "p50_ms": 0.7126265000000003, "p95_ms": 0.7521960000000003, "population_std_ms": 0.015924308283642965 }, "collective": { "mean_ms": 0.5009256875, "n": 16, "p50_ms": 0.5015225, "p95_ms": 0.5122899999999999, "population_std_ms": 0.0051018101287526214 }, "linear_norm_rope": { "mean_ms": 0.8378076250000003, "n": 16, "p50_ms": 0.8377155000000002, "p95_ms": 0.8417550000000004, "population_std_ms": 0.0019228740167716244 }, "moe": { "mean_ms": 1.851001874999998, "n": 16, "p50_ms": 1.8053344999999985, "p95_ms": 1.9718849999999972, "population_std_ms": 0.09850954145403519 }, "other": { "mean_ms": 0.0207508125, "n": 16, "p50_ms": 0.0207035, "p95_ms": 0.021217, "population_std_ms": 0.00025922799297867157 }, "output_head": { "mean_ms": 0.0454381875, "n": 16, "p50_ms": 0.045216, "p95_ms": 0.046560000000000004, "population_std_ms": 0.0004811869723337822 }, "router": { "mean_ms": 0.1865970625, "n": 16, "p50_ms": 0.1865795, "p95_ms": 0.18706799999999996, "population_std_ms": 0.00018487748265743356 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_2(2)": 16 }, "execute_wall": { "mean_ms": 4.6191813125, "n": 16, "p50_ms": 4.5577369999999995, "p95_ms": 4.785498, "population_std_ms": 0.12056056733428579 }, "gpu_kernel_busy": { "mean_ms": 4.164656499999998, "n": 16, "p50_ms": 4.105473, "p95_ms": 4.326126999999998, "population_std_ms": 0.11950220623590964 }, "non_kernel_gap": { "mean_ms": 0.4545248125000018, "n": 16, "p50_ms": 0.45509500000000225, "p95_ms": 0.45937100000000175, "population_std_ms": 0.0031089089770119727 }, "selected_execute_annotation": "execute_context_0(0)_generation_2(2)", "steps": 16, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-batch-tp4-b2-r2-20260723-20260723T090307191004Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b2-r2/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784797602726796969.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.7246866249999998, "n": 16, "p50_ms": 0.7141314999999997, "p95_ms": 0.7533139999999997, "population_std_ms": 0.016680379828840117 }, "collective": { "mean_ms": 0.71273025, "n": 16, "p50_ms": 0.7052324999999999, "p95_ms": 0.7373889999999999, "population_std_ms": 0.01757743828214172 }, "linear_norm_rope": { "mean_ms": 0.8347086875000002, "n": 16, "p50_ms": 0.8344474999999999, "p95_ms": 0.8372729999999998, "population_std_ms": 0.0011941147724752546 }, "moe": { "mean_ms": 1.6199748125000002, "n": 16, "p50_ms": 1.5786544999999998, "p95_ms": 1.7316220000000002, "population_std_ms": 0.08667323273307787 }, "other": { "mean_ms": 0.0206221875, "n": 16, "p50_ms": 0.0206095, "p95_ms": 0.021182, "population_std_ms": 0.0003110010487823955 }, "output_head": { "mean_ms": 0.0457541875, "n": 16, "p50_ms": 0.0456, "p95_ms": 0.04736, "population_std_ms": 0.0005682590978979142 }, "router": { "mean_ms": 0.18685312499999993, "n": 16, "p50_ms": 0.1868349999999999, "p95_ms": 0.18742899999999987, "population_std_ms": 0.00024282758157795687 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_2(2)": 16 }, "execute_wall": { "mean_ms": 4.6185679375, "n": 16, "p50_ms": 4.559101999999999, "p95_ms": 4.787310000000001, "population_std_ms": 0.12219376749832045 }, "gpu_kernel_busy": { "mean_ms": 4.145329875, "n": 16, "p50_ms": 4.0855665, "p95_ms": 4.30906, "population_std_ms": 0.12076811704868254 }, "non_kernel_gap": { "mean_ms": 0.4732380625000001, "n": 16, "p50_ms": 0.47285649999999935, "p95_ms": 0.47825000000000095, "population_std_ms": 0.0030751450874057767 }, "selected_execute_annotation": "execute_context_0(0)_generation_2(2)", "steps": 16, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-batch-tp4-b2-r2-20260723-20260723T090307191004Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b2-r2/traces/profile/dp0_pp0_tp2_dcp0_ep2_rank2.1784797602710411107.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.7193456250000001, "n": 16, "p50_ms": 0.7110120000000001, "p95_ms": 0.7488160000000005, "population_std_ms": 0.0156480688619834 }, "collective": { "mean_ms": 0.5057242500000001, "n": 16, "p50_ms": 0.5041895000000001, "p95_ms": 0.5194939999999999, "population_std_ms": 0.00615956476242434 }, "linear_norm_rope": { "mean_ms": 0.8364726875, "n": 16, "p50_ms": 0.8363539999999998, "p95_ms": 0.84147, "population_std_ms": 0.0026977789873977565 }, "moe": { "mean_ms": 1.8484552499999982, "n": 16, "p50_ms": 1.8005024999999995, "p95_ms": 1.9741669999999973, "population_std_ms": 0.09999423839808207 }, "other": { "mean_ms": 0.020790375, "n": 16, "p50_ms": 0.020800000000000003, "p95_ms": 0.021249999999999998, "population_std_ms": 0.000248934699017634 }, "output_head": { "mean_ms": 0.0455321875, "n": 16, "p50_ms": 0.045424, "p95_ms": 0.046304000000000005, "population_std_ms": 0.00037697981026011215 }, "router": { "mean_ms": 0.18660449999999998, "n": 16, "p50_ms": 0.1866215, "p95_ms": 0.18684699999999987, "population_std_ms": 0.00013768759929635568 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_2(2)": 16 }, "execute_wall": { "mean_ms": 4.617897375, "n": 16, "p50_ms": 4.558091500000001, "p95_ms": 4.783308, "population_std_ms": 0.12193403131912922 }, "gpu_kernel_busy": { "mean_ms": 4.162924874999998, "n": 16, "p50_ms": 4.102588, "p95_ms": 4.328206999999998, "population_std_ms": 0.12156658812810923 }, "non_kernel_gap": { "mean_ms": 0.4549725000000015, "n": 16, "p50_ms": 0.45506600000000175, "p95_ms": 0.4593380000000007, "population_std_ms": 0.002668184377999502 }, "selected_execute_annotation": "execute_context_0(0)_generation_2(2)", "steps": 16, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-batch-tp4-b2-r2-20260723-20260723T090307191004Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b2-r2/traces/profile/dp0_pp0_tp3_dcp0_ep3_rank3.1784797602728757539.pt.trace.json.gz" } ], "schema": "frontier-decode-batch-trace.v1" }