{ "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-r1", "rank_summary": { "component_rank_mean_ms": { "attention": 0.926535269230769, "collective": 0.5587644230769231, "linear_norm_rope": 0.8382221538461538, "moe": 2.378592788461537, "other": 0.02582126923076923, "output_head": 0.048266576923076926, "router": 0.1886060961538461 }, "ranks": 4, "slowest_rank_execute_mean_ms": 5.43262976923077, "slowest_rank_kernel_busy_mean_ms": 4.971441538461537 }, "ranks": [ { "components": { "attention": { "mean_ms": 0.9201209999999999, "n": 13, "p50_ms": 0.920411, "p95_ms": 0.9225939999999999, "population_std_ms": 0.0019136943731553082 }, "collective": { "mean_ms": 0.5660879230769231, "n": 13, "p50_ms": 0.5659190000000001, "p95_ms": 0.5763190000000002, "population_std_ms": 0.005072051101743609 }, "linear_norm_rope": { "mean_ms": 0.8359634615384616, "n": 13, "p50_ms": 0.8359020000000003, "p95_ms": 0.8375410000000001, "population_std_ms": 0.0010538181579662785 }, "moe": { "mean_ms": 2.3794084615384605, "n": 13, "p50_ms": 2.3725099999999975, "p95_ms": 2.4436449999999983, "population_std_ms": 0.038306336006573204 }, "other": { "mean_ms": 0.025853076923076923, "n": 13, "p50_ms": 0.025792, "p95_ms": 0.026593, "population_std_ms": 0.0003076432653223938 }, "output_head": { "mean_ms": 0.04835438461538462, "n": 13, "p50_ms": 0.048193, "p95_ms": 0.048991999999999994, "population_std_ms": 0.0003663435836776379 }, "router": { "mean_ms": 0.18904192307692302, "n": 13, "p50_ms": 0.1891829999999999, "p95_ms": 0.1920339999999999, "population_std_ms": 0.0016883016710719592 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_1(1)": 1, "execute_context_0(0)_generation_6(6)": 13, "execute_context_2(2049)_generation_4(4)": 1, "execute_context_4(8191)_generation_1(1)": 1 }, "execute_wall": { "mean_ms": 5.431982538461539, "n": 13, "p50_ms": 5.424736, "p95_ms": 5.495328000000001, "population_std_ms": 0.03904621042109629 }, "gpu_kernel_busy": { "mean_ms": 4.96483023076923, "n": 13, "p50_ms": 4.958829999999999, "p95_ms": 5.028786999999998, "population_std_ms": 0.0381875548699665 }, "non_kernel_gap": { "mean_ms": 0.46715230769230887, "n": 13, "p50_ms": 0.46785100000000135, "p95_ms": 0.4726150000000029, "population_std_ms": 0.0034291495555826275 }, "selected_execute_annotation": "execute_context_0(0)_generation_6(6)", "steps": 13, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b6-r1-20260723-20260723T091102857920Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b6-r1/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784798079116726333.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.9270714615384612, "n": 13, "p50_ms": 0.9273969999999994, "p95_ms": 0.9299869999999996, "population_std_ms": 0.0017639532793125299 }, "collective": { "mean_ms": 0.5647607692307692, "n": 13, "p50_ms": 0.5641320000000001, "p95_ms": 0.5718079999999998, "population_std_ms": 0.004140332932615274 }, "linear_norm_rope": { "mean_ms": 0.8313579230769229, "n": 13, "p50_ms": 0.8313590000000001, "p95_ms": 0.8333470000000002, "population_std_ms": 0.0011534636442897947 }, "moe": { "mean_ms": 2.3681258461538452, "n": 13, "p50_ms": 2.3586600000000004, "p95_ms": 2.4394819999999995, "population_std_ms": 0.04033740793290489 }, "other": { "mean_ms": 0.02615892307692308, "n": 13, "p50_ms": 0.026175999999999998, "p95_ms": 0.026528000000000003, "population_std_ms": 0.00026144170155812974 }, "output_head": { "mean_ms": 0.048209615384615385, "n": 13, "p50_ms": 0.048096, "p95_ms": 0.049089, "population_std_ms": 0.0004454711487612834 }, "router": { "mean_ms": 0.1910713846153846, "n": 13, "p50_ms": 0.19120299999999996, "p95_ms": 0.1940459999999999, "population_std_ms": 0.0014778622574756317 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_1(1)": 1, "execute_context_0(0)_generation_6(6)": 13, "execute_context_2(2049)_generation_4(4)": 1, "execute_context_4(8191)_generation_1(1)": 1 }, "execute_wall": { "mean_ms": 5.430220692307693, "n": 13, "p50_ms": 5.419602, "p95_ms": 5.493810000000001, "population_std_ms": 0.03883185853707986 }, "gpu_kernel_busy": { "mean_ms": 4.956755923076922, "n": 13, "p50_ms": 4.948898, "p95_ms": 5.020686999999999, "population_std_ms": 0.039974607321805765 }, "non_kernel_gap": { "mean_ms": 0.4734647692307705, "n": 13, "p50_ms": 0.47312300000000196, "p95_ms": 0.47953300000000176, "population_std_ms": 0.0027594904533504113 }, "selected_execute_annotation": "execute_context_0(0)_generation_6(6)", "steps": 13, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b6-r1-20260723-20260723T091102857920Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b6-r1/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784798079120793210.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.9307573846153845, "n": 13, "p50_ms": 0.930942, "p95_ms": 0.9329269999999996, "population_std_ms": 0.0011322629851124393 }, "collective": { "mean_ms": 0.5509683846153847, "n": 13, "p50_ms": 0.5507769999999997, "p95_ms": 0.559011, "population_std_ms": 0.0047502838868763225 }, "linear_norm_rope": { "mean_ms": 0.8407734615384612, "n": 13, "p50_ms": 0.8405719999999995, "p95_ms": 0.8421149999999998, "population_std_ms": 0.0010200678420412281 }, "moe": { "mean_ms": 2.380922769230769, "n": 13, "p50_ms": 2.3736940000000004, "p95_ms": 2.450815999999999, "population_std_ms": 0.04052726901758431 }, "other": { "mean_ms": 0.025844076923076924, "n": 13, "p50_ms": 0.025858, "p95_ms": 0.026433, "population_std_ms": 0.0004114569725216555 }, "output_head": { "mean_ms": 0.04823130769230769, "n": 13, "p50_ms": 0.048128, "p95_ms": 0.048799999999999996, "population_std_ms": 0.0003355393785477529 }, "router": { "mean_ms": 0.18870923076923074, "n": 13, "p50_ms": 0.18834999999999993, "p95_ms": 0.19122899999999987, "population_std_ms": 0.001473603806155092 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_1(1)": 1, "execute_context_0(0)_generation_6(6)": 13, "execute_context_2(2049)_generation_4(4)": 1, "execute_context_4(8191)_generation_1(1)": 1 }, "execute_wall": { "mean_ms": 5.43262976923077, "n": 13, "p50_ms": 5.423109, "p95_ms": 5.49578, "population_std_ms": 0.039102580987318745 }, "gpu_kernel_busy": { "mean_ms": 4.966206615384615, "n": 13, "p50_ms": 4.956755999999999, "p95_ms": 5.031173999999998, "population_std_ms": 0.039860749997842636 }, "non_kernel_gap": { "mean_ms": 0.46642315384615496, "n": 13, "p50_ms": 0.4660140000000004, "p95_ms": 0.47152800000000017, "population_std_ms": 0.002432888149003149 }, "selected_execute_annotation": "execute_context_0(0)_generation_6(6)", "steps": 13, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b6-r1-20260723-20260723T091102857920Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b6-r1/traces/profile/dp0_pp0_tp2_dcp0_ep2_rank2.1784798079116114132.pt.trace.json.gz" }, { "components": { "attention": { "mean_ms": 0.9281912307692306, "n": 13, "p50_ms": 0.9282559999999997, "p95_ms": 0.9303809999999997, "population_std_ms": 0.0012537519785301848 }, "collective": { "mean_ms": 0.5532406153846153, "n": 13, "p50_ms": 0.5540510000000001, "p95_ms": 0.560127, "population_std_ms": 0.004131487002529642 }, "linear_norm_rope": { "mean_ms": 0.8447937692307695, "n": 13, "p50_ms": 0.8444480000000002, "p95_ms": 0.8477320000000004, "population_std_ms": 0.0012637563149865787 }, "moe": { "mean_ms": 2.385914076923075, "n": 13, "p50_ms": 2.3754019999999985, "p95_ms": 2.4513039999999986, "population_std_ms": 0.03863391885270188 }, "other": { "mean_ms": 0.025429, "n": 13, "p50_ms": 0.025372999999999996, "p95_ms": 0.02592, "population_std_ms": 0.00022032458572960754 }, "output_head": { "mean_ms": 0.048271, "n": 13, "p50_ms": 0.048223999999999996, "p95_ms": 0.049121000000000005, "population_std_ms": 0.0004103602544856638 }, "router": { "mean_ms": 0.18560184615384612, "n": 13, "p50_ms": 0.18550399999999995, "p95_ms": 0.18627299999999997, "population_std_ms": 0.00039899813883387426 } }, "execute_annotation_histogram": { "execute_context_0(0)_generation_1(1)": 1, "execute_context_0(0)_generation_6(6)": 13, "execute_context_2(2049)_generation_4(4)": 1, "execute_context_4(8191)_generation_1(1)": 1 }, "execute_wall": { "mean_ms": 5.429620846153846, "n": 13, "p50_ms": 5.421929, "p95_ms": 5.4902809999999995, "population_std_ms": 0.0385510445131288 }, "gpu_kernel_busy": { "mean_ms": 4.971441538461537, "n": 13, "p50_ms": 4.965375999999999, "p95_ms": 5.033802999999999, "population_std_ms": 0.03898058259148536 }, "non_kernel_gap": { "mean_ms": 0.4581793076923092, "n": 13, "p50_ms": 0.45836400000000044, "p95_ms": 0.46242600000000156, "population_std_ms": 0.002535451754152047 }, "selected_execute_annotation": "execute_context_0(0)_generation_6(6)", "steps": 13, "trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b6-r1-20260723-20260723T091102857920Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b6-r1/traces/profile/dp0_pp0_tp3_dcp0_ep3_rank3.1784798079118504722.pt.trace.json.gz" } ], "schema": "frontier-decode-batch-trace.v1" }