{ "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-b6-r2", "rank_summary": { "component_rank_mean_ms": { "attention": 0.9215755535714284, "collective": 4.099890464285714, "linear_norm_rope": 0.8376546964285715, "moe": 2.383938624999999, "other": 0.02548019642857143, "output_head": 0.04836294642857143, "router": 0.19243757142857137 }, "ranks": 4, "slowest_rank_execute_mean_ms": 10.1569875, "slowest_rank_kernel_busy_mean_ms": 9.689807857142856 }, "ranks": [ { "components": { "attention": { "mean_ms": 0.9138666428571425, "n": 14, "p50_ms": 0.9139704999999996, "p95_ms": 0.9164179999999996, "population_std_ms": 0.0016477326242507631 }, "collective": { "mean_ms": 5.290839214285713, "n": 14, "p50_ms": 0.5740495000000001, "p95_ms": 28.996437999999984, "population_std_ms": 9.010484784994565 }, "linear_norm_rope": { "mean_ms": 0.8356119285714287, "n": 14, "p50_ms": 0.8351870000000001, "p95_ms": 0.8384630000000003, "population_std_ms": 0.0012410830215286587 }, "moe": { "mean_ms": 2.382082642857142, "n": 14, "p50_ms": 2.368174999999999, "p95_ms": 2.4507140000000005, "population_std_ms": 0.04469279722346926 }, "other": { "mean_ms": 0.025481714285714285, "n": 14, "p50_ms": 0.025521000000000002, "p95_ms": 0.025824, "population_std_ms": 0.00017456289434365226 }, "output_head": { "mean_ms": 0.048274285714285714, "n": 14, "p50_ms": 0.048175499999999996, "p95_ms": 0.048896, "population_std_ms": 0.0003860829719431935 }, "router": { "mean_ms": 0.19008764285714277, "n": 14, "p50_ms": 0.19016149999999996, "p95_ms": 0.1924179999999999, "population_std_ms": 0.001319140120746566 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_6(6)": 14, "execute_context_2(4096)_generation_4(4)": 1, "execute_context_3(6144)_generation_1(1)": 1 }, "execute_wall": { "mean_ms": 10.1569875, "n": 14, "p50_ms": 5.495552, "p95_ms": 33.916852, "population_std_ms": 9.023692546910278 }, "gpu_kernel_busy": { "mean_ms": 9.68624407142857, "n": 14, "p50_ms": 5.0233855, "p95_ms": 33.44527299999998, "population_std_ms": 9.023394784605482 }, "non_kernel_gap": { "mean_ms": 0.4707434285714301, "n": 14, "p50_ms": 0.47161650000001076, "p95_ms": 0.47796200000000066, "population_std_ms": 0.004213033072914231 }, "selected_execute_annotation": "execute_context_0(0)_generation_6(6)", "steps": 14, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b6-r2-20260723-20260723T092332531885Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b6-r2/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784798836346445272.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.9236260714285712, "n": 14, "p50_ms": 0.9236309999999999, "p95_ms": 0.9261099999999999, "population_std_ms": 0.0016452857964623058 }, "collective": { "mean_ms": 5.292963285714286, "n": 14, "p50_ms": 0.5790519999999999, "p95_ms": 28.995478000000002, "population_std_ms": 9.00940907489549 }, "linear_norm_rope": { "mean_ms": 0.8306526428571429, "n": 14, "p50_ms": 0.8308655000000003, "p95_ms": 0.8323229999999998, "population_std_ms": 0.001215001387838325 }, "moe": { "mean_ms": 2.372463214285713, "n": 14, "p50_ms": 2.3604929999999986, "p95_ms": 2.4334759999999993, "population_std_ms": 0.04456007217899188 }, "other": { "mean_ms": 0.025364571428571427, "n": 14, "p50_ms": 0.025328499999999997, "p95_ms": 0.025759999999999998, "population_std_ms": 0.00018273154168487357 }, "output_head": { "mean_ms": 0.04847557142857143, "n": 14, "p50_ms": 0.048352, "p95_ms": 0.049377000000000004, "population_std_ms": 0.00036324720317195205 }, "router": { "mean_ms": 0.1902149285714285, "n": 14, "p50_ms": 0.1895669999999999, "p95_ms": 0.19510299999999997, "population_std_ms": 0.002332658767044482 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_6(6)": 14, "execute_context_2(4096)_generation_4(4)": 1, "execute_context_3(6144)_generation_1(1)": 1 }, "execute_wall": { "mean_ms": 10.156081571428572, "n": 14, "p50_ms": 5.49357, "p95_ms": 33.919204, "population_std_ms": 9.024698774226101 }, "gpu_kernel_busy": { "mean_ms": 9.683760285714284, "n": 14, "p50_ms": 5.019874, "p95_ms": 33.448195, "population_std_ms": 9.025241580098282 }, "non_kernel_gap": { "mean_ms": 0.47232128571428716, "n": 14, "p50_ms": 0.47191050000000256, "p95_ms": 0.47722900000000035, "population_std_ms": 0.002093886660480702 }, "selected_execute_annotation": "execute_context_0(0)_generation_6(6)", "steps": 14, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b6-r2-20260723-20260723T092332531885Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b6-r2/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784798836333019388.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.9213676428571428, "n": 14, "p50_ms": 0.921938, "p95_ms": 0.9297530000000004, "population_std_ms": 0.004745679668425435 }, "collective": { "mean_ms": 5.281759785714286, "n": 14, "p50_ms": 0.5755820000000003, "p95_ms": 28.99219900000001, "population_std_ms": 9.010812440241091 }, "linear_norm_rope": { "mean_ms": 0.840441214285714, "n": 14, "p50_ms": 0.8404519999999995, "p95_ms": 0.8441329999999994, "population_std_ms": 0.0019087839501543548 }, "moe": { "mean_ms": 2.3862941428571425, "n": 14, "p50_ms": 2.373951, "p95_ms": 2.459937000000001, "population_std_ms": 0.04582171989953023 }, "other": { "mean_ms": 0.025662357142857143, "n": 14, "p50_ms": 0.0256645, "p95_ms": 0.026143999999999997, "population_std_ms": 0.00029092699308610424 }, "output_head": { "mean_ms": 0.048436714285714284, "n": 14, "p50_ms": 0.048575999999999994, "p95_ms": 0.048991999999999994, "population_std_ms": 0.0004154401157759286 }, "router": { "mean_ms": 0.18584599999999996, "n": 14, "p50_ms": 0.185825, "p95_ms": 0.18636899999999995, "population_std_ms": 0.00029020731505990466 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_6(6)": 14, "execute_context_2(4096)_generation_4(4)": 1, "execute_context_3(6144)_generation_1(1)": 1 }, "execute_wall": { "mean_ms": 10.156770214285714, "n": 14, "p50_ms": 5.493733, "p95_ms": 33.916464999999995, "population_std_ms": 9.023992692816982 }, "gpu_kernel_busy": { "mean_ms": 9.689807857142856, "n": 14, "p50_ms": 5.033896, "p95_ms": 33.45033900000001, "population_std_ms": 9.02452540636983 }, "non_kernel_gap": { "mean_ms": 0.4669623571428573, "n": 14, "p50_ms": 0.467391000000001, "p95_ms": 0.47341499999999836, "population_std_ms": 0.004137908505636468 }, "selected_execute_annotation": "execute_context_0(0)_generation_6(6)", "steps": 14, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b6-r2-20260723-20260723T092332531885Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b6-r2/traces/profile/dp0_pp0_tp2_dcp0_ep2_rank2.1784798836334934191.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.9274418571428571, "n": 14, "p50_ms": 0.9274730000000002, "p95_ms": 0.9312359999999998, "population_std_ms": 0.0016344587071277954 }, "collective": { "mean_ms": 0.5339995714285714, "n": 14, "p50_ms": 0.5353115, "p95_ms": 0.5461410000000002, "population_std_ms": 0.006859063864846362 }, "linear_norm_rope": { "mean_ms": 0.8439130000000005, "n": 14, "p50_ms": 0.8440930000000004, "p95_ms": 0.8451400000000011, "population_std_ms": 0.000779706171763452 }, "moe": { "mean_ms": 2.3949144999999987, "n": 14, "p50_ms": 2.386371499999999, "p95_ms": 2.457828999999998, "population_std_ms": 0.044398212431438724 }, "other": { "mean_ms": 0.02541214285714286, "n": 14, "p50_ms": 0.0254395, "p95_ms": 0.025761999999999997, "population_std_ms": 0.00027587053307739895 }, "output_head": { "mean_ms": 0.048265214285714286, "n": 14, "p50_ms": 0.048063999999999996, "p95_ms": 0.049057, "population_std_ms": 0.00045419413385081205 }, "router": { "mean_ms": 0.20360171428571425, "n": 14, "p50_ms": 0.20369749999999998, "p95_ms": 0.20981799999999995, "population_std_ms": 0.0021429506170088787 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_6(6)": 14, "execute_context_2(4096)_generation_4(4)": 1, "execute_context_3(6144)_generation_1(1)": 1 }, "execute_wall": { "mean_ms": 10.156985785714285, "n": 14, "p50_ms": 5.495433, "p95_ms": 33.916939, "population_std_ms": 9.023746050846789 }, "gpu_kernel_busy": { "mean_ms": 4.977547999999999, "n": 14, "p50_ms": 4.961732999999999, "p95_ms": 5.047107999999999, "population_std_ms": 0.04773951894694539 }, "non_kernel_gap": { "mean_ms": 5.179437785714287, "n": 14, "p50_ms": 0.4635420000000008, "p95_ms": 28.877357, "population_std_ms": 9.007091777202437 }, "selected_execute_annotation": "execute_context_0(0)_generation_6(6)", "steps": 14, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b6-r2-20260723-20260723T092332531885Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b6-r2/traces/profile/dp0_pp0_tp3_dcp0_ep3_rank3.1784798836405275119.pt.trace.json.gz" } ], "schema": "frontier-decode-batch-trace.v1" }