{ "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-r1", "rank_summary": { "component_rank_mean_ms": { "attention": 0.72195021875, "collective": 0.553751203125, "linear_norm_rope": 0.8375226249999999, "moe": 1.7999987343749986, "other": 0.020717078125, "output_head": 0.0456011875, "router": 0.18689503124999995 }, "ranks": 4, "slowest_rank_execute_mean_ms": 4.6262738125, "slowest_rank_kernel_busy_mean_ms": 4.1718804999999985 }, "ranks": [ { "components": { "attention": { "mean_ms": 0.721057875, "n": 16, "p50_ms": 0.711759, "p95_ms": 0.7497570000000005, "population_std_ms": 0.014212609814329528 }, "collective": { "mean_ms": 0.50711625, "n": 16, "p50_ms": 0.5068694999999999, "p95_ms": 0.513504, "population_std_ms": 0.004382496085280639 }, "linear_norm_rope": { "mean_ms": 0.8348696874999997, "n": 16, "p50_ms": 0.8344809999999998, "p95_ms": 0.838978, "population_std_ms": 0.001855606192014971 }, "moe": { "mean_ms": 1.8552162499999982, "n": 16, "p50_ms": 1.8067699999999989, "p95_ms": 1.9758739999999988, "population_std_ms": 0.09932662894681066 }, "other": { "mean_ms": 0.020664125, "n": 16, "p50_ms": 0.0206075, "p95_ms": 0.02112, "population_std_ms": 0.00022492384127744221 }, "output_head": { "mean_ms": 0.0455501875, "n": 16, "p50_ms": 0.045616500000000004, "p95_ms": 0.046176, "population_std_ms": 0.0003880140491576959 }, "router": { "mean_ms": 0.18695149999999994, "n": 16, "p50_ms": 0.18694599999999995, "p95_ms": 0.18726899999999994, "population_std_ms": 0.00018246506514945761 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_2(2)": 16 }, "execute_wall": { "mean_ms": 4.6235766875, "n": 16, "p50_ms": 4.5675045, "p95_ms": 4.776305000000001, "population_std_ms": 0.11774099993349754 }, "gpu_kernel_busy": { "mean_ms": 4.171425874999998, "n": 16, "p50_ms": 4.111105499999998, "p95_ms": 4.327753999999999, "population_std_ms": 0.11827515014357118 }, "non_kernel_gap": { "mean_ms": 0.4521508125000021, "n": 16, "p50_ms": 0.4516910000000025, "p95_ms": 0.4587190000000012, "population_std_ms": 0.003134758388192225 }, "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-r1-20260723-20260723T085748513290Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b2-r1/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784797289133609908.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.7231355625, "n": 16, "p50_ms": 0.714801, "p95_ms": 0.7511429999999999, "population_std_ms": 0.01670948629135843 }, "collective": { "mean_ms": 0.5030436875000001, "n": 16, "p50_ms": 0.5025615000000001, "p95_ms": 0.5099899999999999, "population_std_ms": 0.003726454090666345 }, "linear_norm_rope": { "mean_ms": 0.8384581250000002, "n": 16, "p50_ms": 0.8374080000000004, "p95_ms": 0.8426070000000001, "population_std_ms": 0.0022757014818238397 }, "moe": { "mean_ms": 1.8538525624999982, "n": 16, "p50_ms": 1.8066204999999975, "p95_ms": 1.980685999999996, "population_std_ms": 0.0992721840478037 }, "other": { "mean_ms": 0.02081575, "n": 16, "p50_ms": 0.020768000000000002, "p95_ms": 0.021249000000000004, "population_std_ms": 0.00024472216389203553 }, "output_head": { "mean_ms": 0.0455743125, "n": 16, "p50_ms": 0.045568, "p95_ms": 0.046335999999999995, "population_std_ms": 0.00038872157753815117 }, "router": { "mean_ms": 0.18700049999999993, "n": 16, "p50_ms": 0.18708599999999992, "p95_ms": 0.18729799999999988, "population_std_ms": 0.0002492310674855524 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_2(2)": 16 }, "execute_wall": { "mean_ms": 4.624022875, "n": 16, "p50_ms": 4.5670969999999995, "p95_ms": 4.776058, "population_std_ms": 0.11785700086167718 }, "gpu_kernel_busy": { "mean_ms": 4.1718804999999985, "n": 16, "p50_ms": 4.113653999999998, "p95_ms": 4.327779999999995, "population_std_ms": 0.11872818612749433 }, "non_kernel_gap": { "mean_ms": 0.4521423750000019, "n": 16, "p50_ms": 0.452637500000002, "p95_ms": 0.4561850000000023, "population_std_ms": 0.002606323557115182 }, "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-r1-20260723-20260723T085748513290Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b2-r1/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784797289127939045.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.7228365624999997, "n": 16, "p50_ms": 0.7140979999999998, "p95_ms": 0.7481270000000001, "population_std_ms": 0.014826216615208781 }, "collective": { "mean_ms": 0.6974953125000001, "n": 16, "p50_ms": 0.6933765000000001, "p95_ms": 0.7296940000000001, "population_std_ms": 0.019150322023136917 }, "linear_norm_rope": { "mean_ms": 0.8396519374999999, "n": 16, "p50_ms": 0.8394079999999997, "p95_ms": 0.8423959999999997, "population_std_ms": 0.0015175569786975635 }, "moe": { "mean_ms": 1.6409965000000004, "n": 16, "p50_ms": 1.6039915000000007, "p95_ms": 1.749915000000001, "population_std_ms": 0.08420929796569343 }, "other": { "mean_ms": 0.0206121875, "n": 16, "p50_ms": 0.020608, "p95_ms": 0.021438, "population_std_ms": 0.0003990141317594523 }, "output_head": { "mean_ms": 0.0457240625, "n": 16, "p50_ms": 0.04584, "p95_ms": 0.046816, "population_std_ms": 0.0005658698468674145 }, "router": { "mean_ms": 0.18694024999999992, "n": 16, "p50_ms": 0.18695999999999993, "p95_ms": 0.18755099999999994, "population_std_ms": 0.00021861224233788088 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_2(2)": 16 }, "execute_wall": { "mean_ms": 4.6262738125, "n": 16, "p50_ms": 4.569678, "p95_ms": 4.780622, "population_std_ms": 0.11869307020905795 }, "gpu_kernel_busy": { "mean_ms": 4.1542568125, "n": 16, "p50_ms": 4.100302, "p95_ms": 4.307204000000001, "population_std_ms": 0.11747190161545976 }, "non_kernel_gap": { "mean_ms": 0.47201699999999974, "n": 16, "p50_ms": 0.47202699999999975, "p95_ms": 0.47818999999999967, "population_std_ms": 0.0027272721719696818 }, "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-r1-20260723-20260723T085748513290Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b2-r1/traces/profile/dp0_pp0_tp2_dcp0_ep2_rank2.1784797289123687444.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.720770875, "n": 16, "p50_ms": 0.7128364999999999, "p95_ms": 0.7470090000000001, "population_std_ms": 0.01543277700170565 }, "collective": { "mean_ms": 0.5073495625, "n": 16, "p50_ms": 0.5075825, "p95_ms": 0.514207, "population_std_ms": 0.004872701393589966 }, "linear_norm_rope": { "mean_ms": 0.8371107499999998, "n": 16, "p50_ms": 0.8368309999999997, "p95_ms": 0.8408340000000005, "population_std_ms": 0.0019278550742989576 }, "moe": { "mean_ms": 1.849929624999998, "n": 16, "p50_ms": 1.8029354999999985, "p95_ms": 1.9727399999999982, "population_std_ms": 0.09810616143359367 }, "other": { "mean_ms": 0.02077625, "n": 16, "p50_ms": 0.020671500000000002, "p95_ms": 0.021408, "population_std_ms": 0.00033703143399392235 }, "output_head": { "mean_ms": 0.0455561875, "n": 16, "p50_ms": 0.045392, "p95_ms": 0.046880000000000005, "population_std_ms": 0.0004960692011642635 }, "router": { "mean_ms": 0.18668787499999998, "n": 16, "p50_ms": 0.18664099999999995, "p95_ms": 0.18707300000000002, "population_std_ms": 0.00021251878593432893 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_2(2)": 16 }, "execute_wall": { "mean_ms": 4.623365625, "n": 16, "p50_ms": 4.5671315, "p95_ms": 4.775658999999999, "population_std_ms": 0.11841808903936239 }, "gpu_kernel_busy": { "mean_ms": 4.168181124999998, "n": 16, "p50_ms": 4.109987499999998, "p95_ms": 4.320808999999999, "population_std_ms": 0.1170474600631484 }, "non_kernel_gap": { "mean_ms": 0.45518450000000205, "n": 16, "p50_ms": 0.45484250000000115, "p95_ms": 0.46047800000000283, "population_std_ms": 0.0026128110101962454 }, "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-r1-20260723-20260723T085748513290Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b2-r1/traces/profile/dp0_pp0_tp3_dcp0_ep3_rank3.1784797289132564461.pt.trace.json.gz" } ], "schema": "frontier-decode-batch-trace.v1" }