{ "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-b6-r2", "rank_summary": { "component_rank_mean_ms": { "attention": 1.0463109615384618, "collective": 0.48337815384615385, "linear_norm_rope": 0.929004346153846, "moe": 3.7078099230769217, "other": 0.025587923076923078, "output_head": 0.08800392307692309, "router": 0.19478769230769236 }, "ranks": 2, "slowest_rank_execute_mean_ms": 6.9378406923076925, "slowest_rank_kernel_busy_mean_ms": 6.477923153846153 }, "ranks": [ { "components": { "attention": { "mean_ms": 1.0448520000000003, "n": 13, "p50_ms": 1.045254000000001, "p95_ms": 1.0465970000000002, "population_std_ms": 0.0012648827856913572 }, "collective": { "mean_ms": 0.4906066923076923, "n": 13, "p50_ms": 0.48854500000000006, "p95_ms": 0.5128349999999999, "population_std_ms": 0.007319711768018179 }, "linear_norm_rope": { "mean_ms": 0.9276054615384616, "n": 13, "p50_ms": 0.927922, "p95_ms": 0.9300229999999996, "population_std_ms": 0.0012124997456231853 }, "moe": { "mean_ms": 3.7032171538461522, "n": 13, "p50_ms": 3.6941509999999984, "p95_ms": 3.9345319999999977, "population_std_ms": 0.18506379688215108 }, "other": { "mean_ms": 0.02531215384615385, "n": 13, "p50_ms": 0.025345, "p95_ms": 0.025984, "population_std_ms": 0.0003609239950148982 }, "output_head": { "mean_ms": 0.08801007692307693, "n": 13, "p50_ms": 0.087968, "p95_ms": 0.08851200000000001, "population_std_ms": 0.0003446964018777317 }, "router": { "mean_ms": 0.19831961538461543, "n": 13, "p50_ms": 0.1956510000000001, "p95_ms": 0.23433300000000007, "population_std_ms": 0.010532589860037432 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_1(1)": 1, "execute_context_0(0)_generation_6(6)": 13, "execute_context_2(2049)_generation_4(4)": 1, "execute_context_4(8191)_generation_1(1)": 1 }, "execute_wall": { "mean_ms": 6.937815615384616, "n": 13, "p50_ms": 6.920955, "p95_ms": 7.177563, "population_std_ms": 0.17465452547487034 }, "gpu_kernel_busy": { "mean_ms": 6.477923153846153, "n": 13, "p50_ms": 6.464021999999998, "p95_ms": 6.714968999999998, "population_std_ms": 0.17390358211193135 }, "non_kernel_gap": { "mean_ms": 0.4598924615384625, "n": 13, "p50_ms": 0.46010100000000165, "p95_ms": 0.4628480000000019, "population_std_ms": 0.0022957863280165477 }, "selected_execute_annotation": "execute_context_0(0)_generation_6(6)", "steps": 13, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp2-b6-r2-20260723-20260723T093020293408Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b6-r2/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784799236964172371.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 1.0477699230769233, "n": 13, "p50_ms": 1.0473580000000002, "p95_ms": 1.0502500000000003, "population_std_ms": 0.0016845846994043283 }, "collective": { "mean_ms": 0.47614961538461537, "n": 13, "p50_ms": 0.47488799999999987, "p95_ms": 0.4852860000000001, "population_std_ms": 0.006279926721013708 }, "linear_norm_rope": { "mean_ms": 0.9304032307692304, "n": 13, "p50_ms": 0.9300610000000001, "p95_ms": 0.9343409999999996, "population_std_ms": 0.0015794439213190966 }, "moe": { "mean_ms": 3.712402692307691, "n": 13, "p50_ms": 3.7038869999999973, "p95_ms": 3.951868000000003, "population_std_ms": 0.18554981438267218 }, "other": { "mean_ms": 0.02586369230769231, "n": 13, "p50_ms": 0.025888, "p95_ms": 0.026400000000000003, "population_std_ms": 0.0002951522122606689 }, "output_head": { "mean_ms": 0.08799776923076924, "n": 13, "p50_ms": 0.087937, "p95_ms": 0.088992, "population_std_ms": 0.00042456876834413246 }, "router": { "mean_ms": 0.19125576923076928, "n": 13, "p50_ms": 0.18793900000000005, "p95_ms": 0.23312300000000005, "population_std_ms": 0.012158267147240543 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_1(1)": 1, "execute_context_0(0)_generation_6(6)": 13, "execute_context_2(2049)_generation_4(4)": 1, "execute_context_4(8191)_generation_1(1)": 1 }, "execute_wall": { "mean_ms": 6.9378406923076925, "n": 13, "p50_ms": 6.920646, "p95_ms": 7.1769359999999995, "population_std_ms": 0.17404824161814114 }, "gpu_kernel_busy": { "mean_ms": 6.471842692307691, "n": 13, "p50_ms": 6.4540469999999965, "p95_ms": 6.708258000000003, "population_std_ms": 0.17518788350506015 }, "non_kernel_gap": { "mean_ms": 0.465998000000001, "n": 13, "p50_ms": 0.4667860000000026, "p95_ms": 0.4705280000000025, "population_std_ms": 0.0037250578518997 }, "selected_execute_annotation": "execute_context_0(0)_generation_6(6)", "steps": 13, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp2-b6-r2-20260723-20260723T093020293408Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b6-r2/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784799236965538368.pt.trace.json.gz" } ], "schema": "frontier-decode-batch-trace.v1" }