{ "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-b4-r2", "rank_summary": { "component_rank_mean_ms": { "attention": 0.801226767857143, "collective": 0.6577525357142857, "linear_norm_rope": 0.8391043928571427, "moe": 1.9621030178571435, "other": 0.021777, "output_head": 0.045781142857142854, "router": 0.18946453571428562 }, "ranks": 4, "slowest_rank_execute_mean_ms": 4.726592071428572, "slowest_rank_kernel_busy_mean_ms": 4.601115500000001 }, "ranks": [ { "components": { "attention": { "mean_ms": 0.8019157857142859, "n": 14, "p50_ms": 0.8018870000000005, "p95_ms": 0.8074610000000003, "population_std_ms": 0.0036870609313142864 }, "collective": { "mean_ms": 0.697091642857143, "n": 14, "p50_ms": 0.521808, "p95_ms": 1.635147000000001, "population_std_ms": 0.3581717548612294 }, "linear_norm_rope": { "mean_ms": 0.8477593571428571, "n": 14, "p50_ms": 0.847532, "p95_ms": 0.8513850000000003, "population_std_ms": 0.0016779822750273288 }, "moe": { "mean_ms": 1.9648232142857136, "n": 14, "p50_ms": 1.9675199999999988, "p95_ms": 2.1313579999999983, "population_std_ms": 0.11544109651690553 }, "other": { "mean_ms": 0.022008857142857143, "n": 14, "p50_ms": 0.022, "p95_ms": 0.022559999999999997, "population_std_ms": 0.0003089169692288703 }, "output_head": { "mean_ms": 0.045711999999999996, "n": 14, "p50_ms": 0.045792, "p95_ms": 0.046144, "population_std_ms": 0.0003498834499821745 }, "router": { "mean_ms": 0.18900892857142845, "n": 14, "p50_ms": 0.1890704999999999, "p95_ms": 0.18972699999999987, "population_std_ms": 0.0003452439022500138 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_4(4)": 14, "execute_context_1(2048)_generation_1(1)": 1, "execute_context_2(4096)_generation_2(2)": 1 }, "execute_wall": { "mean_ms": 4.726289, "n": 14, "p50_ms": 4.587623499999999, "p95_ms": 6.343786, "population_std_ms": 0.5295863492605742 }, "gpu_kernel_busy": { "mean_ms": 4.568319785714285, "n": 14, "p50_ms": 4.476973999999999, "p95_ms": 5.5797930000000004, "population_std_ms": 0.3971815245092024 }, "non_kernel_gap": { "mean_ms": 0.15796921428571484, "n": 14, "p50_ms": 0.11138250000000127, "p95_ms": 0.7639929999999993, "population_std_ms": 0.1680896761222489 }, "selected_execute_annotation": "execute_context_0(0)_generation_4(4)", "steps": 14, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b4-r2-20260723-20260723T092328819959Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b4-r2/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784798849005052042.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.7960197142857144, "n": 14, "p50_ms": 0.7975315000000003, "p95_ms": 0.8016960000000003, "population_std_ms": 0.005350704885854841 }, "collective": { "mean_ms": 0.5697055714285714, "n": 14, "p50_ms": 0.527951, "p95_ms": 1.1241249999999998, "population_std_ms": 0.15379550779651446 }, "linear_norm_rope": { "mean_ms": 0.8354554285714284, "n": 14, "p50_ms": 0.8356854999999999, "p95_ms": 0.8373729999999999, "population_std_ms": 0.0013868995078585018 }, "moe": { "mean_ms": 1.9646907142857157, "n": 14, "p50_ms": 1.9679745000000008, "p95_ms": 2.128705000000001, "population_std_ms": 0.11638566052410722 }, "other": { "mean_ms": 0.021556214285714286, "n": 14, "p50_ms": 0.021551, "p95_ms": 0.022076000000000002, "population_std_ms": 0.000275473923726115 }, "output_head": { "mean_ms": 0.045609142857142855, "n": 14, "p50_ms": 0.045504, "p95_ms": 0.046592, "population_std_ms": 0.00037677557873977814 }, "router": { "mean_ms": 0.1894397142857142, "n": 14, "p50_ms": 0.18942449999999988, "p95_ms": 0.19078299999999992, "population_std_ms": 0.0005227123530983776 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_4(4)": 14, "execute_context_1(2048)_generation_1(1)": 1, "execute_context_2(4096)_generation_2(2)": 1 }, "execute_wall": { "mean_ms": 4.726592071428572, "n": 14, "p50_ms": 4.587085, "p95_ms": 6.349746, "population_std_ms": 0.5316654164241782 }, "gpu_kernel_busy": { "mean_ms": 4.422476500000001, "n": 14, "p50_ms": 4.384860500000001, "p95_ms": 5.0564160000000005, "population_std_ms": 0.21186941717878632 }, "non_kernel_gap": { "mean_ms": 0.3041155714285702, "n": 14, "p50_ms": 0.12178199999999872, "p95_ms": 1.2933299999999992, "population_std_ms": 0.3691441767122035 }, "selected_execute_annotation": "execute_context_0(0)_generation_4(4)", "steps": 14, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b4-r2-20260723-20260723T092328819959Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b4-r2/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784798849005338612.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.8045258571428573, "n": 14, "p50_ms": 0.8049890000000001, "p95_ms": 0.8098900000000004, "population_std_ms": 0.003910280750920532 }, "collective": { "mean_ms": 0.7413481428571427, "n": 14, "p50_ms": 0.523762, "p95_ms": 2.205729, "population_std_ms": 0.47534174936067347 }, "linear_norm_rope": { "mean_ms": 0.8360086428571426, "n": 14, "p50_ms": 0.8361784999999999, "p95_ms": 0.837317, "population_std_ms": 0.0010630517127015252 }, "moe": { "mean_ms": 1.9618675000000008, "n": 14, "p50_ms": 1.9661850000000007, "p95_ms": 2.119519000000001, "population_std_ms": 0.1151975200022925 }, "other": { "mean_ms": 0.02169592857142857, "n": 14, "p50_ms": 0.021664500000000003, "p95_ms": 0.022047999999999998, "population_std_ms": 0.00024448267957514905 }, "output_head": { "mean_ms": 0.04594742857142858, "n": 14, "p50_ms": 0.045984000000000004, "p95_ms": 0.046784, "population_std_ms": 0.0004970469529827017 }, "router": { "mean_ms": 0.18972199999999992, "n": 14, "p50_ms": 0.1897264999999999, "p95_ms": 0.1903659999999999, "population_std_ms": 0.00040084571310453965 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_4(4)": 14, "execute_context_1(2048)_generation_1(1)": 1, "execute_context_2(4096)_generation_2(2)": 1 }, "execute_wall": { "mean_ms": 4.725667642857142, "n": 14, "p50_ms": 4.586822, "p95_ms": 6.3431750000000005, "population_std_ms": 0.5294299685093403 }, "gpu_kernel_busy": { "mean_ms": 4.601115500000001, "n": 14, "p50_ms": 4.466799, "p95_ms": 6.1463090000000005, "population_std_ms": 0.5125165009938357 }, "non_kernel_gap": { "mean_ms": 0.12455214285714243, "n": 14, "p50_ms": 0.11967999999999934, "p95_ms": 0.19686599999999999, "population_std_ms": 0.020164973440020648 }, "selected_execute_annotation": "execute_context_0(0)_generation_4(4)", "steps": 14, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b4-r2-20260723-20260723T092328819959Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b4-r2/traces/profile/dp0_pp0_tp2_dcp0_ep2_rank2.1784798849004512081.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.8024457142857144, "n": 14, "p50_ms": 0.8021285000000002, "p95_ms": 0.8093020000000001, "population_std_ms": 0.005437250978581053 }, "collective": { "mean_ms": 0.6228647857142856, "n": 14, "p50_ms": 0.52369, "p95_ms": 1.3911020000000003, "population_std_ms": 0.2490648031124713 }, "linear_norm_rope": { "mean_ms": 0.8371941428571427, "n": 14, "p50_ms": 0.8375324999999998, "p95_ms": 0.8382489999999997, "population_std_ms": 0.00103632529760148 }, "moe": { "mean_ms": 1.9570306428571438, "n": 14, "p50_ms": 1.9613605000000005, "p95_ms": 2.1156430000000004, "population_std_ms": 0.11617949366611671 }, "other": { "mean_ms": 0.021847000000000002, "n": 14, "p50_ms": 0.021792, "p95_ms": 0.022240000000000003, "population_std_ms": 0.0002032686470096729 }, "output_head": { "mean_ms": 0.045856, "n": 14, "p50_ms": 0.04592, "p95_ms": 0.046272, "population_std_ms": 0.00036146388873183906 }, "router": { "mean_ms": 0.18968749999999987, "n": 14, "p50_ms": 0.18976349999999986, "p95_ms": 0.1904969999999999, "population_std_ms": 0.0004998125005582514 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_4(4)": 14, "execute_context_1(2048)_generation_1(1)": 1, "execute_context_2(4096)_generation_2(2)": 1 }, "execute_wall": { "mean_ms": 4.726361142857143, "n": 14, "p50_ms": 4.58896, "p95_ms": 6.346271, "population_std_ms": 0.5297092372787245 }, "gpu_kernel_busy": { "mean_ms": 4.476925785714287, "n": 14, "p50_ms": 4.454530500000001, "p95_ms": 5.177472, "population_std_ms": 0.28127072648585827 }, "non_kernel_gap": { "mean_ms": 0.2494353571428564, "n": 14, "p50_ms": 0.12384599999999946, "p95_ms": 1.887349999999997, "population_std_ms": 0.4542784406329925 }, "selected_execute_annotation": "execute_context_0(0)_generation_4(4)", "steps": 14, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b4-r2-20260723-20260723T092328819959Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b4-r2/traces/profile/dp0_pp0_tp3_dcp0_ep3_rank3.1784798849009637378.pt.trace.json.gz" } ], "schema": "frontier-decode-batch-trace.v1" }