186 lines
5.9 KiB
JSON
186 lines
5.9 KiB
JSON
{
|
|
"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-b2-r2",
|
|
"rank_summary": {
|
|
"component_rank_mean_ms": {
|
|
"attention": 0.7975021874999999,
|
|
"collective": 0.44700175,
|
|
"linear_norm_rope": 0.9334021562499997,
|
|
"moe": 2.1485421874999986,
|
|
"other": 0.02076096875,
|
|
"output_head": 0.08701734375,
|
|
"router": 0.19057953124999993
|
|
},
|
|
"ranks": 2,
|
|
"slowest_rank_execute_mean_ms": 4.7298366875,
|
|
"slowest_rank_kernel_busy_mean_ms": 4.625673687499998
|
|
},
|
|
"ranks": [
|
|
{
|
|
"components": {
|
|
"attention": {
|
|
"mean_ms": 0.7957946874999998,
|
|
"n": 16,
|
|
"p50_ms": 0.7977499999999997,
|
|
"p95_ms": 0.8024729999999999,
|
|
"population_std_ms": 0.0050081016328389115
|
|
},
|
|
"collective": {
|
|
"mean_ms": 0.4559536875,
|
|
"n": 16,
|
|
"p50_ms": 0.44857899999999995,
|
|
"p95_ms": 0.5749780000000001,
|
|
"population_std_ms": 0.03100173565044134
|
|
},
|
|
"linear_norm_rope": {
|
|
"mean_ms": 0.9314522499999998,
|
|
"n": 16,
|
|
"p50_ms": 0.9312219999999996,
|
|
"p95_ms": 0.9362239999999998,
|
|
"population_std_ms": 0.0018965892906741145
|
|
},
|
|
"moe": {
|
|
"mean_ms": 2.144734312499999,
|
|
"n": 16,
|
|
"p50_ms": 2.2638159999999994,
|
|
"p95_ms": 2.2729309999999985,
|
|
"population_std_ms": 0.16050482071137254
|
|
},
|
|
"other": {
|
|
"mean_ms": 0.0205803125,
|
|
"n": 16,
|
|
"p50_ms": 0.020513,
|
|
"p95_ms": 0.021342,
|
|
"population_std_ms": 0.00034404573074483917
|
|
},
|
|
"output_head": {
|
|
"mean_ms": 0.0869003125,
|
|
"n": 16,
|
|
"p50_ms": 0.086897,
|
|
"p95_ms": 0.087585,
|
|
"population_std_ms": 0.0003536547961554459
|
|
},
|
|
"router": {
|
|
"mean_ms": 0.19025812499999992,
|
|
"n": 16,
|
|
"p50_ms": 0.19022449999999994,
|
|
"p95_ms": 0.19071799999999992,
|
|
"population_std_ms": 0.00028991245984778943
|
|
}
|
|
},
|
|
"execute_annotation_histogram": {
|
|
"execute_context_0(0)_generation_2(2)": 16
|
|
},
|
|
"execute_wall": {
|
|
"mean_ms": 4.72958625,
|
|
"n": 16,
|
|
"p50_ms": 4.841987,
|
|
"p95_ms": 4.974675,
|
|
"population_std_ms": 0.1744621378768544
|
|
},
|
|
"gpu_kernel_busy": {
|
|
"mean_ms": 4.625673687499998,
|
|
"n": 16,
|
|
"p50_ms": 4.7410514999999975,
|
|
"p95_ms": 4.871186999999999,
|
|
"population_std_ms": 0.1763796075070467
|
|
},
|
|
"non_kernel_gap": {
|
|
"mean_ms": 0.10391256250000158,
|
|
"n": 16,
|
|
"p50_ms": 0.10354800000000175,
|
|
"p95_ms": 0.10959400000000219,
|
|
"population_std_ms": 0.0028733005187579386
|
|
},
|
|
"selected_execute_annotation": "execute_context_0(0)_generation_2(2)",
|
|
"steps": 16,
|
|
"trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp2-b2-r2-20260723-20260723T092320882080Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b2-r2/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784798812071346091.pt.trace.json.gz"
|
|
},
|
|
{
|
|
"components": {
|
|
"attention": {
|
|
"mean_ms": 0.7992096874999999,
|
|
"n": 16,
|
|
"p50_ms": 0.8017949999999999,
|
|
"p95_ms": 0.8056339999999999,
|
|
"population_std_ms": 0.00523807464292403
|
|
},
|
|
"collective": {
|
|
"mean_ms": 0.4380498125,
|
|
"n": 16,
|
|
"p50_ms": 0.4294910000000001,
|
|
"p95_ms": 0.56768,
|
|
"population_std_ms": 0.033749115542519664
|
|
},
|
|
"linear_norm_rope": {
|
|
"mean_ms": 0.9353520624999997,
|
|
"n": 16,
|
|
"p50_ms": 0.9359214999999996,
|
|
"p95_ms": 0.9375480000000005,
|
|
"population_std_ms": 0.0017075802861340613
|
|
},
|
|
"moe": {
|
|
"mean_ms": 2.1523500624999987,
|
|
"n": 16,
|
|
"p50_ms": 2.2702614999999993,
|
|
"p95_ms": 2.284628,
|
|
"population_std_ms": 0.16187233535855888
|
|
},
|
|
"other": {
|
|
"mean_ms": 0.020941625000000002,
|
|
"n": 16,
|
|
"p50_ms": 0.0209265,
|
|
"p95_ms": 0.021598,
|
|
"population_std_ms": 0.0003365376789826063
|
|
},
|
|
"output_head": {
|
|
"mean_ms": 0.087134375,
|
|
"n": 16,
|
|
"p50_ms": 0.087281,
|
|
"p95_ms": 0.087585,
|
|
"population_std_ms": 0.0004719001317810776
|
|
},
|
|
"router": {
|
|
"mean_ms": 0.19090093749999995,
|
|
"n": 16,
|
|
"p50_ms": 0.19088099999999994,
|
|
"p95_ms": 0.19164899999999993,
|
|
"population_std_ms": 0.0003892426089134459
|
|
}
|
|
},
|
|
"execute_annotation_histogram": {
|
|
"execute_context_0(0)_generation_2(2)": 16
|
|
},
|
|
"execute_wall": {
|
|
"mean_ms": 4.7298366875,
|
|
"n": 16,
|
|
"p50_ms": 4.8450835,
|
|
"p95_ms": 4.970972,
|
|
"population_std_ms": 0.1741141631820623
|
|
},
|
|
"gpu_kernel_busy": {
|
|
"mean_ms": 4.6239385624999985,
|
|
"n": 16,
|
|
"p50_ms": 4.7412614999999985,
|
|
"p95_ms": 4.869705999999997,
|
|
"population_std_ms": 0.17688744584409086
|
|
},
|
|
"non_kernel_gap": {
|
|
"mean_ms": 0.10589812500000201,
|
|
"n": 16,
|
|
"p50_ms": 0.10663300000000042,
|
|
"p95_ms": 0.11212500000000247,
|
|
"population_std_ms": 0.003380934446920671
|
|
},
|
|
"selected_execute_annotation": "execute_context_0(0)_generation_2(2)",
|
|
"steps": 16,
|
|
"trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp2-b2-r2-20260723-20260723T092320882080Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b2-r2/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784798812076480600.pt.trace.json.gz"
|
|
}
|
|
],
|
|
"schema": "frontier-decode-batch-trace.v1"
|
|
}
|