{ "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-r2", "rank_summary": { "component_rank_mean_ms": { "attention": 1.400657307692308, "collective": 0.5005616923076923, "linear_norm_rope": 0.9316651538461536, "moe": 2.69281696153846, "other": 0.023672576923076925, "output_head": 0.08830773076923076, "router": 0.1908271153846154 }, "ranks": 2, "slowest_rank_execute_mean_ms": 6.309095692307692, "slowest_rank_kernel_busy_mean_ms": 5.828548538461537 }, "ranks": [ { "components": { "attention": { "mean_ms": 1.4095765384615386, "n": 13, "p50_ms": 1.4091810000000007, "p95_ms": 1.4131269999999998, "population_std_ms": 0.0017758118236840018 }, "collective": { "mean_ms": 0.4864672307692308, "n": 13, "p50_ms": 0.4871060000000002, "p95_ms": 0.5083250000000001, "population_std_ms": 0.007854287590999577 }, "linear_norm_rope": { "mean_ms": 0.9326894615384612, "n": 13, "p50_ms": 0.9327419999999998, "p95_ms": 0.9343809999999997, "population_std_ms": 0.001099693356936376 }, "moe": { "mean_ms": 2.692551615384614, "n": 13, "p50_ms": 2.7793569999999983, "p95_ms": 2.871725999999997, "population_std_ms": 0.17050402067063422 }, "other": { "mean_ms": 0.024125384615384618, "n": 13, "p50_ms": 0.024064000000000002, "p95_ms": 0.024864000000000008, "population_std_ms": 0.00029315092948108124 }, "output_head": { "mean_ms": 0.08821176923076922, "n": 13, "p50_ms": 0.08828799999999999, "p95_ms": 0.088672, "population_std_ms": 0.0004720397887150791 }, "router": { "mean_ms": 0.19492653846153846, "n": 13, "p50_ms": 0.19584, "p95_ms": 0.19798399999999997, "population_std_ms": 0.002327761308652399 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_8(8)": 13, "execute_context_2(2051)_generation_6(6)": 1, "execute_context_2(4096)_generation_1(1)": 1, "execute_context_4(8189)_generation_3(3)": 1 }, "execute_wall": { "mean_ms": 6.309095692307692, "n": 13, "p50_ms": 6.398511, "p95_ms": 6.483886999999999, "population_std_ms": 0.1703797844741088 }, "gpu_kernel_busy": { "mean_ms": 5.828548538461537, "n": 13, "p50_ms": 5.915967999999998, "p95_ms": 6.002267999999997, "population_std_ms": 0.17012899737805992 }, "non_kernel_gap": { "mean_ms": 0.4805471538461554, "n": 13, "p50_ms": 0.4803160000000002, "p95_ms": 0.4859510000000009, "population_std_ms": 0.0025392862972511096 }, "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-r2-20260723-20260723T093023994242Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b8-r2/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784799245841164026.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 1.3917380769230774, "n": 13, "p50_ms": 1.3920280000000005, "p95_ms": 1.3950360000000008, "population_std_ms": 0.001887833412693738 }, "collective": { "mean_ms": 0.5146561538461538, "n": 13, "p50_ms": 0.5156739999999999, "p95_ms": 0.5248290000000001, "population_std_ms": 0.00624208518964558 }, "linear_norm_rope": { "mean_ms": 0.9306408461538459, "n": 13, "p50_ms": 0.9303399999999994, "p95_ms": 0.9336909999999994, "population_std_ms": 0.0015690834093706387 }, "moe": { "mean_ms": 2.693082307692306, "n": 13, "p50_ms": 2.778146, "p95_ms": 2.867843999999997, "population_std_ms": 0.17102703603069247 }, "other": { "mean_ms": 0.02321976923076923, "n": 13, "p50_ms": 0.023139, "p95_ms": 0.023648000000000002, "population_std_ms": 0.00028077369859458957 }, "output_head": { "mean_ms": 0.08840369230769231, "n": 13, "p50_ms": 0.08832, "p95_ms": 0.089408, "population_std_ms": 0.0004100955582104095 }, "router": { "mean_ms": 0.18672769230769232, "n": 13, "p50_ms": 0.18675, "p95_ms": 0.189218, "population_std_ms": 0.0011293141134617489 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_8(8)": 13, "execute_context_2(2051)_generation_6(6)": 1, "execute_context_2(4096)_generation_1(1)": 1, "execute_context_4(8189)_generation_3(3)": 1 }, "execute_wall": { "mean_ms": 6.307694615384615, "n": 13, "p50_ms": 6.399717, "p95_ms": 6.488933, "population_std_ms": 0.17066632055317688 }, "gpu_kernel_busy": { "mean_ms": 5.828468538461537, "n": 13, "p50_ms": 5.9137319999999995, "p95_ms": 6.007808999999997, "population_std_ms": 0.17195541813398352 }, "non_kernel_gap": { "mean_ms": 0.4792260769230788, "n": 13, "p50_ms": 0.4783710000000063, "p95_ms": 0.4893030000000005, "population_std_ms": 0.00435339587097986 }, "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-r2-20260723-20260723T093023994242Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b8-r2/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784799245841819751.pt.trace.json.gz" } ], "schema": "frontier-decode-batch-trace.v1" }