{ "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-b8-r1", "rank_summary": { "component_rank_mean_ms": { "attention": 0.9206188846153844, "collective": 0.6864052307692307, "linear_norm_rope": 0.8407714807692306, "moe": 2.0225017884615384, "other": 0.023575519230769233, "output_head": 0.04601186538461538, "router": 0.19361455769230762 }, "ranks": 4, "slowest_rank_execute_mean_ms": 4.898132615384616, "slowest_rank_kernel_busy_mean_ms": 4.786881538461537 }, "ranks": [ { "components": { "attention": { "mean_ms": 0.9177004615384619, "n": 13, "p50_ms": 0.9157820000000005, "p95_ms": 0.9225340000000003, "population_std_ms": 0.0034723709615584538 }, "collective": { "mean_ms": 0.7274665384615383, "n": 13, "p50_ms": 0.5518440000000001, "p95_ms": 1.9667529999999998, "population_std_ms": 0.43009803968337174 }, "linear_norm_rope": { "mean_ms": 0.8444890769230771, "n": 13, "p50_ms": 0.8439450000000001, "p95_ms": 0.8488609999999996, "population_std_ms": 0.0016826488943849141 }, "moe": { "mean_ms": 2.0259989230769215, "n": 13, "p50_ms": 1.988923999999999, "p95_ms": 2.1999619999999984, "population_std_ms": 0.12419348290932108 }, "other": { "mean_ms": 0.023444076923076925, "n": 13, "p50_ms": 0.023455999999999998, "p95_ms": 0.023873, "population_std_ms": 0.00022429083507407156 }, "output_head": { "mean_ms": 0.046225461538461535, "n": 13, "p50_ms": 0.046369, "p95_ms": 0.046944, "population_std_ms": 0.00042185881987381115 }, "router": { "mean_ms": 0.20155699999999996, "n": 13, "p50_ms": 0.20153599999999994, "p95_ms": 0.2069459999999999, "population_std_ms": 0.0028213344905722135 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_1(1)": 1, "execute_context_0(0)_generation_8(8)": 13, "execute_context_4(6145)_generation_4(4)": 1, "execute_context_4(8191)_generation_1(1)": 1 }, "execute_wall": { "mean_ms": 4.898132615384616, "n": 13, "p50_ms": 4.671016, "p95_ms": 6.300266, "population_std_ms": 0.4965030281369486 }, "gpu_kernel_busy": { "mean_ms": 4.786881538461537, "n": 13, "p50_ms": 4.558992999999998, "p95_ms": 6.188288999999999, "population_std_ms": 0.49662703894922927 }, "non_kernel_gap": { "mean_ms": 0.11125107692307844, "n": 13, "p50_ms": 0.11197700000000044, "p95_ms": 0.11466700000000163, "population_std_ms": 0.0023827902345303826 }, "selected_execute_annotation": "execute_context_0(0)_generation_8(8)", "steps": 13, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b8-r1-20260723-20260723T091720058921Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b8-r1/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784798477249293674.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.920315615384615, "n": 13, "p50_ms": 0.9189889999999995, "p95_ms": 0.9261809999999997, "population_std_ms": 0.004422100328306619 }, "collective": { "mean_ms": 0.5528313846153846, "n": 13, "p50_ms": 0.5527689999999998, "p95_ms": 0.5607639999999999, "population_std_ms": 0.006298594807127897 }, "linear_norm_rope": { "mean_ms": 0.8396410769230767, "n": 13, "p50_ms": 0.8399539999999995, "p95_ms": 0.8417579999999998, "population_std_ms": 0.0011731414408487047 }, "moe": { "mean_ms": 2.02596976923077, "n": 13, "p50_ms": 1.9839060000000013, "p95_ms": 2.2111380000000014, "population_std_ms": 0.1288343954994783 }, "other": { "mean_ms": 0.023620923076923078, "n": 13, "p50_ms": 0.023712, "p95_ms": 0.024191, "population_std_ms": 0.00032006452751773154 }, "output_head": { "mean_ms": 0.045848769230769235, "n": 13, "p50_ms": 0.045729, "p95_ms": 0.046465000000000006, "population_std_ms": 0.0003160560208001501 }, "router": { "mean_ms": 0.1913852307692307, "n": 13, "p50_ms": 0.1909419999999999, "p95_ms": 0.19360099999999988, "population_std_ms": 0.0011535338449135141 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_1(1)": 1, "execute_context_0(0)_generation_8(8)": 13, "execute_context_4(6145)_generation_4(4)": 1, "execute_context_4(8191)_generation_1(1)": 1 }, "execute_wall": { "mean_ms": 4.897705538461539, "n": 13, "p50_ms": 4.67211, "p95_ms": 6.299505, "population_std_ms": 0.4965302476577009 }, "gpu_kernel_busy": { "mean_ms": 4.599612769230769, "n": 13, "p50_ms": 4.552709000000001, "p95_ms": 4.782309000000001, "population_std_ms": 0.13015763047648984 }, "non_kernel_gap": { "mean_ms": 0.2980927692307692, "n": 13, "p50_ms": 0.12020799999999987, "p95_ms": 1.5448980000000008, "population_std_ms": 0.4320880301128383 }, "selected_execute_annotation": "execute_context_0(0)_generation_8(8)", "steps": 13, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b8-r1-20260723-20260723T091720058921Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b8-r1/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784798477252917819.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.9192469230769227, "n": 13, "p50_ms": 0.918141, "p95_ms": 0.9271450000000001, "population_std_ms": 0.004336312124402079 }, "collective": { "mean_ms": 0.7371800769230769, "n": 13, "p50_ms": 0.5602280000000001, "p95_ms": 1.9925419999999985, "population_std_ms": 0.43457656793648614 }, "linear_norm_rope": { "mean_ms": 0.838645769230769, "n": 13, "p50_ms": 0.8387470000000002, "p95_ms": 0.8435129999999993, "population_std_ms": 0.0020585651894104804 }, "moe": { "mean_ms": 2.016775461538462, "n": 13, "p50_ms": 1.9734350000000007, "p95_ms": 2.202970000000001, "population_std_ms": 0.12585738148372902 }, "other": { "mean_ms": 0.023712538461538462, "n": 13, "p50_ms": 0.023677999999999998, "p95_ms": 0.024418000000000002, "population_std_ms": 0.00033176465601725676 }, "output_head": { "mean_ms": 0.04599407692307692, "n": 13, "p50_ms": 0.045984000000000004, "p95_ms": 0.046912, "population_std_ms": 0.00044461590364622505 }, "router": { "mean_ms": 0.1922016153846153, "n": 13, "p50_ms": 0.19241399999999995, "p95_ms": 0.1942349999999999, "population_std_ms": 0.0013174549204643176 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_1(1)": 1, "execute_context_0(0)_generation_8(8)": 13, "execute_context_4(6145)_generation_4(4)": 1, "execute_context_4(8191)_generation_1(1)": 1 }, "execute_wall": { "mean_ms": 4.895284846153846, "n": 13, "p50_ms": 4.669829, "p95_ms": 6.300007, "population_std_ms": 0.49721882332999884 }, "gpu_kernel_busy": { "mean_ms": 4.773756461538461, "n": 13, "p50_ms": 4.548986, "p95_ms": 6.178948, "population_std_ms": 0.49733430942307366 }, "non_kernel_gap": { "mean_ms": 0.12152838461538465, "n": 13, "p50_ms": 0.1210589999999998, "p95_ms": 0.12582700000000013, "population_std_ms": 0.0025302041431304327 }, "selected_execute_annotation": "execute_context_0(0)_generation_8(8)", "steps": 13, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b8-r1-20260723-20260723T091720058921Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b8-r1/traces/profile/dp0_pp0_tp2_dcp0_ep2_rank2.1784798477249455220.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.9252125384615381, "n": 13, "p50_ms": 0.9248339999999994, "p95_ms": 0.9334720000000002, "population_std_ms": 0.00510464326509754 }, "collective": { "mean_ms": 0.728142923076923, "n": 13, "p50_ms": 0.5495350000000001, "p95_ms": 1.9773729999999994, "population_std_ms": 0.43309947849824937 }, "linear_norm_rope": { "mean_ms": 0.8403099999999996, "n": 13, "p50_ms": 0.8403849999999997, "p95_ms": 0.8420689999999995, "population_std_ms": 0.0010695695755409923 }, "moe": { "mean_ms": 2.0212630000000003, "n": 13, "p50_ms": 1.9823120000000007, "p95_ms": 2.2015650000000004, "population_std_ms": 0.12667332402498332 }, "other": { "mean_ms": 0.02352453846153846, "n": 13, "p50_ms": 0.02352, "p95_ms": 0.023999000000000003, "population_std_ms": 0.0002336379893321535 }, "output_head": { "mean_ms": 0.04597915384615384, "n": 13, "p50_ms": 0.04592, "p95_ms": 0.046784, "population_std_ms": 0.0004999015050916534 }, "router": { "mean_ms": 0.18931438461538452, "n": 13, "p50_ms": 0.18934399999999993, "p95_ms": 0.18963499999999994, "population_std_ms": 0.00023338826628654523 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_1(1)": 1, "execute_context_0(0)_generation_8(8)": 13, "execute_context_4(6145)_generation_4(4)": 1, "execute_context_4(8191)_generation_1(1)": 1 }, "execute_wall": { "mean_ms": 4.895507769230769, "n": 13, "p50_ms": 4.665760000000001, "p95_ms": 6.301792000000001, "population_std_ms": 0.49796797169854445 }, "gpu_kernel_busy": { "mean_ms": 4.773746538461538, "n": 13, "p50_ms": 4.544830999999999, "p95_ms": 6.177703999999999, "population_std_ms": 0.49768554496537193 }, "non_kernel_gap": { "mean_ms": 0.12176123076923144, "n": 13, "p50_ms": 0.12077500000000008, "p95_ms": 0.128610000000001, "population_std_ms": 0.0033113621913244884 }, "selected_execute_annotation": "execute_context_0(0)_generation_8(8)", "steps": 13, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b8-r1-20260723-20260723T091720058921Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b8-r1/traces/profile/dp0_pp0_tp3_dcp0_ep3_rank3.1784798477250211216.pt.trace.json.gz" } ], "schema": "frontier-decode-batch-trace.v1" }