{ "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-b4-r2", "rank_summary": { "component_rank_mean_ms": { "attention": 0.9231347666666667, "collective": 0.47522929999999997, "linear_norm_rope": 0.9270692666666666, "moe": 2.523926433333333, "other": 0.021883766666666665, "output_head": 0.08742516666666666, "router": 0.18552376666666665 }, "ranks": 2, "slowest_rank_execute_mean_ms": 5.606906066666666, "slowest_rank_kernel_busy_mean_ms": 5.148062666666666 }, "ranks": [ { "components": { "attention": { "mean_ms": 0.9221591999999998, "n": 15, "p50_ms": 0.9204839999999996, "p95_ms": 0.9305610000000001, "population_std_ms": 0.0055392075630603605 }, "collective": { "mean_ms": 0.47690353333333335, "n": 15, "p50_ms": 0.4750740000000001, "p95_ms": 0.5079370000000001, "population_std_ms": 0.008762698616801168 }, "linear_norm_rope": { "mean_ms": 0.9266067333333331, "n": 15, "p50_ms": 0.9269229999999996, "p95_ms": 0.9281389999999996, "population_std_ms": 0.001160841388342339 }, "moe": { "mean_ms": 2.5183345333333333, "n": 15, "p50_ms": 2.535845999999999, "p95_ms": 2.6756949999999993, "population_std_ms": 0.11626729790436485 }, "other": { "mean_ms": 0.0223382, "n": 15, "p50_ms": 0.022207, "p95_ms": 0.022974, "population_std_ms": 0.00033397688542772 }, "output_head": { "mean_ms": 0.08742633333333334, "n": 15, "p50_ms": 0.08752, "p95_ms": 0.088224, "population_std_ms": 0.00039636644100573626 }, "router": { "mean_ms": 0.18655373333333325, "n": 15, "p50_ms": 0.1865609999999999, "p95_ms": 0.1867189999999999, "population_std_ms": 0.00011684261018805013 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_4(4)": 15, "execute_context_1(2048)_generation_3(3)": 1 }, "execute_wall": { "mean_ms": 5.606906066666666, "n": 15, "p50_ms": 5.649197, "p95_ms": 5.755214, "population_std_ms": 0.1162303895094949 }, "gpu_kernel_busy": { "mean_ms": 5.140322266666667, "n": 15, "p50_ms": 5.182554999999998, "p95_ms": 5.287060999999999, "population_std_ms": 0.11673111694743465 }, "non_kernel_gap": { "mean_ms": 0.4665838000000001, "n": 15, "p50_ms": 0.466642000000002, "p95_ms": 0.47348399999999913, "population_std_ms": 0.003150324304998906 }, "selected_execute_annotation": "execute_context_0(0)_generation_4(4)", "steps": 15, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp2-b4-r2-20260723-20260723T092324802748Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b4-r2/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784798821005851469.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.9241103333333336, "n": 15, "p50_ms": 0.9240880000000004, "p95_ms": 0.9288660000000003, "population_std_ms": 0.0027653286403045273 }, "collective": { "mean_ms": 0.47355506666666664, "n": 15, "p50_ms": 0.4710439999999998, "p95_ms": 0.5040649999999999, "population_std_ms": 0.008578622861249649 }, "linear_norm_rope": { "mean_ms": 0.9275318, "n": 15, "p50_ms": 0.927647, "p95_ms": 0.9290880000000004, "population_std_ms": 0.0009876329412624172 }, "moe": { "mean_ms": 2.529518333333333, "n": 15, "p50_ms": 2.546805999999999, "p95_ms": 2.682659999999999, "population_std_ms": 0.11457118978560389 }, "other": { "mean_ms": 0.021429333333333335, "n": 15, "p50_ms": 0.021312000000000005, "p95_ms": 0.022112, "population_std_ms": 0.0003245893131669962 }, "output_head": { "mean_ms": 0.087424, "n": 15, "p50_ms": 0.087488, "p95_ms": 0.087936, "population_std_ms": 0.0003762779114785578 }, "router": { "mean_ms": 0.1844938, "n": 15, "p50_ms": 0.18451400000000007, "p95_ms": 0.18483299999999994, "population_std_ms": 0.0001811099849998921 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_4(4)": 15, "execute_context_1(2048)_generation_3(3)": 1 }, "execute_wall": { "mean_ms": 5.6060968, "n": 15, "p50_ms": 5.65066, "p95_ms": 5.7521, "population_std_ms": 0.1166928070969243 }, "gpu_kernel_busy": { "mean_ms": 5.148062666666666, "n": 15, "p50_ms": 5.194570999999999, "p95_ms": 5.294759999999998, "population_std_ms": 0.11587941756076509 }, "non_kernel_gap": { "mean_ms": 0.45803413333333365, "n": 15, "p50_ms": 0.4584260000000002, "p95_ms": 0.4647389999999998, "population_std_ms": 0.003347060996688631 }, "selected_execute_annotation": "execute_context_0(0)_generation_4(4)", "steps": 15, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp2-b4-r2-20260723-20260723T092324802748Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b4-r2/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784798821004197352.pt.trace.json.gz" } ], "schema": "frontier-decode-batch-trace.v1" }