Profile decode batch grid repeats

This commit is contained in:
2026-07-23 17:37:18 +08:00
parent 1126d9be7d
commit ecc5599381
16 changed files with 3679 additions and 13 deletions

View File

@@ -30,12 +30,14 @@ def parse_args() -> argparse.Namespace:
def main() -> None: def main() -> None:
args = parse_args() args = parse_args()
cells = [] cells = []
all_stable = True all_resolved = True
for tp in (2, 4): for tp in (2, 4):
for batch in (2, 4, 6, 8): for batch in (2, 4, 6, 8):
repeats = [] repeats = []
for repeat in (1, 2): for repeat in (1, 2, 3):
path = args.results_dir / f"tp{tp}-b{batch}-r{repeat}.json" path = args.results_dir / f"tp{tp}-b{batch}-r{repeat}.json"
if repeat == 3 and not path.exists():
continue
payload = json.loads(path.read_text()) payload = json.loads(path.read_text())
repeats.append( repeats.append(
{ {
@@ -50,18 +52,28 @@ def main() -> None:
} }
) )
values = [row["execute_mean_ms"] for row in repeats] values = [row["execute_mean_ms"] for row in repeats]
mean = statistics.fmean(values) initial_values = values[:2]
cv_pct = statistics.pstdev(values) / mean * 100.0 initial_mean = statistics.fmean(initial_values)
stable = cv_pct <= 10.0 initial_cv_pct = (
all_stable = all_stable and stable statistics.pstdev(initial_values) / initial_mean * 100.0
)
needs_repeat_3 = initial_cv_pct > 10.0
repeat_gate_resolved = not needs_repeat_3 or len(repeats) == 3
all_resolved = all_resolved and repeat_gate_resolved
cells.append( cells.append(
{ {
"tp": tp, "tp": tp,
"batch": batch, "batch": batch,
"repeats": repeats, "repeats": repeats,
"median_execute_ms": statistics.median(values), "median_execute_ms": statistics.median(values),
"repeat_cv_pct": cv_pct, "initial_repeat_cv_pct": initial_cv_pct,
"stable": stable, "all_repeat_cv_pct": (
statistics.pstdev(values)
/ statistics.fmean(values)
* 100.0
),
"needs_repeat_3": needs_repeat_3,
"repeat_gate_resolved": repeat_gate_resolved,
"median_component_ms": { "median_component_ms": {
name: statistics.median( name: statistics.median(
row["component_rank_mean_ms"][name] for row in repeats row["component_rank_mean_ms"][name] for row in repeats
@@ -75,16 +87,16 @@ def main() -> None:
"contract": { "contract": {
"workload": "Qwen3-30B-A3B BF16, 2048->128, graph-on, MNS=16", "workload": "Qwen3-30B-A3B BF16, 2048->128, graph-on, MNS=16",
"timing": "slowest-rank execute mean over 16 pure-decode steps", "timing": "slowest-rank execute mean over 16 pure-decode steps",
"repeat_aggregation": "median of two fresh engine processes", "repeat_aggregation": "median of two fresh processes; three if unstable",
"stability_gate": "population CV <= 10%; add repeat 3 otherwise", "stability_gate": "r1/r2 population CV <=10%; else require r3 and take median",
}, },
"all_cells_stable": all_stable, "all_repeat_gates_resolved": all_resolved,
"cells": cells, "cells": cells,
} }
args.output.parent.mkdir(parents=True, exist_ok=True) args.output.parent.mkdir(parents=True, exist_ok=True)
args.output.write_text(json.dumps(payload, indent=2, sort_keys=True) + "\n") args.output.write_text(json.dumps(payload, indent=2, sort_keys=True) + "\n")
if not all_stable: if not all_resolved:
raise SystemExit("one or more cells failed the repeat stability gate") raise SystemExit("one or more cells require repeat 3")
if __name__ == "__main__": if __name__ == "__main__":

View File

@@ -0,0 +1,16 @@
version = 1
[[jobs]]
name = "decode-grid-tp4-b6-r3-20260723"
gpus = 4
gpu_model = "H20"
hosts = ["dash4"]
command = "timeout --signal=TERM --kill-after=60s 1800 bash runs/frontier-decode-batch-grid-v0/run_decode_profile.sh"
artifacts = ["runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b6-r3"]
[jobs.env]
TP = "4"
PROFILE_BATCH = "6"
SERVER_PORT = "9844"
OUTPUT_ROOT = "runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b6-r3"
FLASHINFER_WORKSPACE_BASE = "/tmp/frontier-component-flashinfer-v4"

View File

@@ -0,0 +1,185 @@
{
"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-r1",
"rank_summary": {
"component_rank_mean_ms": {
"attention": 0.7962288124999999,
"collective": 0.470928375,
"linear_norm_rope": 0.9330912187499996,
"moe": 2.136206281249999,
"other": 0.02065321875,
"output_head": 0.08696040625000001,
"router": 0.19041484374999995
},
"ranks": 2,
"slowest_rank_execute_mean_ms": 4.7613618125,
"slowest_rank_kernel_busy_mean_ms": 4.657866374999998
},
"ranks": [
{
"components": {
"attention": {
"mean_ms": 0.7951932499999999,
"n": 16,
"p50_ms": 0.7978159999999996,
"p95_ms": 0.8009929999999998,
"population_std_ms": 0.004837302056673742
},
"collective": {
"mean_ms": 0.4532200625,
"n": 16,
"p50_ms": 0.44667250000000003,
"p95_ms": 0.579522,
"population_std_ms": 0.032947570582800075
},
"linear_norm_rope": {
"mean_ms": 0.9318721874999996,
"n": 16,
"p50_ms": 0.9318319999999995,
"p95_ms": 0.9354359999999993,
"population_std_ms": 0.001684765236566671
},
"moe": {
"mean_ms": 2.133037374999999,
"n": 16,
"p50_ms": 2.260420499999999,
"p95_ms": 2.2688760000000006,
"population_std_ms": 0.1538413522138454
},
"other": {
"mean_ms": 0.0205200625,
"n": 16,
"p50_ms": 0.0205595,
"p95_ms": 0.020864,
"population_std_ms": 0.0002014638518289322
},
"output_head": {
"mean_ms": 0.086960375,
"n": 16,
"p50_ms": 0.087073,
"p95_ms": 0.087424,
"population_std_ms": 0.0003634009278675549
},
"router": {
"mean_ms": 0.19029662499999994,
"n": 16,
"p50_ms": 0.19019399999999992,
"p95_ms": 0.19120399999999993,
"population_std_ms": 0.00036799488362612264
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_2(2)": 16
},
"execute_wall": {
"mean_ms": 4.7613618125,
"n": 16,
"p50_ms": 4.842258,
"p95_ms": 5.225267,
"population_std_ms": 0.20309347556335333
},
"gpu_kernel_busy": {
"mean_ms": 4.611099937499998,
"n": 16,
"p50_ms": 4.738485999999997,
"p95_ms": 4.880249,
"population_std_ms": 0.17253325791549196
},
"non_kernel_gap": {
"mean_ms": 0.15026187500000182,
"n": 16,
"p50_ms": 0.10683750000000192,
"p95_ms": 0.7480410000000006,
"population_std_ms": 0.15527935203322837
},
"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-r1-20260723-20260723T091051245390Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b2-r1/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784798066564146891.pt.trace.json.gz"
},
{
"components": {
"attention": {
"mean_ms": 0.7972643749999999,
"n": 16,
"p50_ms": 0.8003265,
"p95_ms": 0.8037429999999999,
"population_std_ms": 0.005557197617448423
},
"collective": {
"mean_ms": 0.4886366875,
"n": 16,
"p50_ms": 0.4386005,
"p95_ms": 1.0788600000000004,
"population_std_ms": 0.15686321799051514
},
"linear_norm_rope": {
"mean_ms": 0.9343102499999997,
"n": 16,
"p50_ms": 0.9339574999999996,
"p95_ms": 0.9376900000000002,
"population_std_ms": 0.0018319578836589897
},
"moe": {
"mean_ms": 2.1393751874999984,
"n": 16,
"p50_ms": 2.2672624999999984,
"p95_ms": 2.276405999999998,
"population_std_ms": 0.15445752086424064
},
"other": {
"mean_ms": 0.020786375,
"n": 16,
"p50_ms": 0.020785,
"p95_ms": 0.021567999999999997,
"population_std_ms": 0.0003711985444139028
},
"output_head": {
"mean_ms": 0.0869604375,
"n": 16,
"p50_ms": 0.087008,
"p95_ms": 0.087937,
"population_std_ms": 0.0004370792217593405
},
"router": {
"mean_ms": 0.19053306249999993,
"n": 16,
"p50_ms": 0.19049349999999995,
"p95_ms": 0.19151799999999988,
"population_std_ms": 0.0003664594910678971
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_2(2)": 16
},
"execute_wall": {
"mean_ms": 4.7613106875,
"n": 16,
"p50_ms": 4.8443950000000005,
"p95_ms": 5.2236769999999995,
"population_std_ms": 0.20362942305009554
},
"gpu_kernel_busy": {
"mean_ms": 4.657866374999998,
"n": 16,
"p50_ms": 4.739760999999998,
"p95_ms": 5.121143999999998,
"population_std_ms": 0.20551660892883905
},
"non_kernel_gap": {
"mean_ms": 0.10344431250000213,
"n": 16,
"p50_ms": 0.10326550000000179,
"p95_ms": 0.10955400000000282,
"population_std_ms": 0.002999292535722995
},
"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-r1-20260723-20260723T091051245390Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b2-r1/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784798066565640462.pt.trace.json.gz"
}
],
"schema": "frontier-decode-batch-trace.v1"
}

View File

@@ -0,0 +1,185 @@
{
"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"
}

View File

@@ -0,0 +1,189 @@
{
"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-r1",
"rank_summary": {
"component_rank_mean_ms": {
"attention": 0.9284945714285713,
"collective": 0.4770398571428571,
"linear_norm_rope": 0.9251340357142854,
"moe": 2.5554174642857146,
"other": 0.021663214285714286,
"output_head": 0.08753164285714285,
"router": 0.1898966428571428
},
"ranks": 2,
"slowest_rank_execute_mean_ms": 5.294425214285715,
"slowest_rank_kernel_busy_mean_ms": 5.187257214285713
},
"ranks": [
{
"components": {
"attention": {
"mean_ms": 0.9336339285714287,
"n": 14,
"p50_ms": 0.933751,
"p95_ms": 0.9427530000000001,
"population_std_ms": 0.0036295537007084476
},
"collective": {
"mean_ms": 0.47076142857142855,
"n": 14,
"p50_ms": 0.4640835000000001,
"p95_ms": 0.5701469999999997,
"population_std_ms": 0.0277061237241214
},
"linear_norm_rope": {
"mean_ms": 0.9244245714285712,
"n": 14,
"p50_ms": 0.9243979999999998,
"p95_ms": 0.9272680000000004,
"population_std_ms": 0.0014581096232689887
},
"moe": {
"mean_ms": 2.554062214285715,
"n": 14,
"p50_ms": 2.594499500000001,
"p95_ms": 2.694474,
"population_std_ms": 0.11681852632925924
},
"other": {
"mean_ms": 0.02227242857142857,
"n": 14,
"p50_ms": 0.022274000000000002,
"p95_ms": 0.022625,
"population_std_ms": 0.00020562612198068582
},
"output_head": {
"mean_ms": 0.087598,
"n": 14,
"p50_ms": 0.08764849999999999,
"p95_ms": 0.088257,
"population_std_ms": 0.00042077038190171175
},
"router": {
"mean_ms": 0.1903450714285714,
"n": 14,
"p50_ms": 0.19036999999999993,
"p95_ms": 0.19091199999999997,
"population_std_ms": 0.00033161088735480956
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_1(1)": 1,
"execute_context_0(0)_generation_4(4)": 14,
"execute_context_3(6144)_generation_1(1)": 1
},
"execute_wall": {
"mean_ms": 5.292617,
"n": 14,
"p50_ms": 5.351565000000001,
"p95_ms": 5.420654000000001,
"population_std_ms": 0.12026193009071014
},
"gpu_kernel_busy": {
"mean_ms": 5.183097642857143,
"n": 14,
"p50_ms": 5.2450280000000005,
"p95_ms": 5.312519,
"population_std_ms": 0.12140493871020902
},
"non_kernel_gap": {
"mean_ms": 0.10951935714285696,
"n": 14,
"p50_ms": 0.1093335000000013,
"p95_ms": 0.11392299999999889,
"population_std_ms": 0.002305499592809895
},
"selected_execute_annotation": "execute_context_0(0)_generation_4(4)",
"steps": 14,
"trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp2-b4-r1-20260723-20260723T091055280404Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b4-r1/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784798075195956333.pt.trace.json.gz"
},
{
"components": {
"attention": {
"mean_ms": 0.9233552142857139,
"n": 14,
"p50_ms": 0.9231514999999997,
"p95_ms": 0.92672,
"population_std_ms": 0.002063045328030955
},
"collective": {
"mean_ms": 0.4833182857142857,
"n": 14,
"p50_ms": 0.47641600000000006,
"p95_ms": 0.5747199999999999,
"population_std_ms": 0.025529410631741578
},
"linear_norm_rope": {
"mean_ms": 0.9258434999999997,
"n": 14,
"p50_ms": 0.9259644999999999,
"p95_ms": 0.9298849999999995,
"population_std_ms": 0.0017809597633218826
},
"moe": {
"mean_ms": 2.556772714285714,
"n": 14,
"p50_ms": 2.5972645000000014,
"p95_ms": 2.697822,
"population_std_ms": 0.11678101165455461
},
"other": {
"mean_ms": 0.021054,
"n": 14,
"p50_ms": 0.021136000000000002,
"p95_ms": 0.021632000000000002,
"population_std_ms": 0.0003493892630617853
},
"output_head": {
"mean_ms": 0.08746528571428572,
"n": 14,
"p50_ms": 0.087424,
"p95_ms": 0.087936,
"population_std_ms": 0.00027621250322672924
},
"router": {
"mean_ms": 0.18944821428571418,
"n": 14,
"p50_ms": 0.1893899999999999,
"p95_ms": 0.18998899999999994,
"population_std_ms": 0.00036123541563669255
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_1(1)": 1,
"execute_context_0(0)_generation_4(4)": 14,
"execute_context_3(6144)_generation_1(1)": 1
},
"execute_wall": {
"mean_ms": 5.294425214285715,
"n": 14,
"p50_ms": 5.3559085,
"p95_ms": 5.420421,
"population_std_ms": 0.12112366521521874
},
"gpu_kernel_busy": {
"mean_ms": 5.187257214285713,
"n": 14,
"p50_ms": 5.247959,
"p95_ms": 5.314969999999999,
"population_std_ms": 0.12129808972773216
},
"non_kernel_gap": {
"mean_ms": 0.10716800000000092,
"n": 14,
"p50_ms": 0.10673850000000096,
"p95_ms": 0.11011199999999732,
"population_std_ms": 0.0018639973942341857
},
"selected_execute_annotation": "execute_context_0(0)_generation_4(4)",
"steps": 14,
"trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp2-b4-r1-20260723-20260723T091055280404Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b4-r1/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784798075201036386.pt.trace.json.gz"
}
],
"schema": "frontier-decode-batch-trace.v1"
}

View File

@@ -0,0 +1,187 @@
{
"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"
}

View File

@@ -0,0 +1,189 @@
{
"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-b6-r1",
"rank_summary": {
"component_rank_mean_ms": {
"attention": 1.0590365714285717,
"collective": 0.48200882142857143,
"linear_norm_rope": 0.9312401785714285,
"moe": 3.678020964285713,
"other": 0.02528782142857143,
"output_head": 0.08801067857142857,
"router": 0.1985437857142856
},
"ranks": 2,
"slowest_rank_execute_mean_ms": 6.570553642857143,
"slowest_rank_kernel_busy_mean_ms": 6.462748499999998
},
"ranks": [
{
"components": {
"attention": {
"mean_ms": 1.056612428571429,
"n": 14,
"p50_ms": 1.0567985000000006,
"p95_ms": 1.0597780000000006,
"population_std_ms": 0.0016962762879018302
},
"collective": {
"mean_ms": 0.4931447857142857,
"n": 14,
"p50_ms": 0.4922715000000001,
"p95_ms": 0.5031650000000001,
"population_std_ms": 0.0056488543235214805
},
"linear_norm_rope": {
"mean_ms": 0.9297670714285715,
"n": 14,
"p50_ms": 0.9300385,
"p95_ms": 0.9327710000000003,
"population_std_ms": 0.0016833948889195887
},
"moe": {
"mean_ms": 3.6738179999999985,
"n": 14,
"p50_ms": 3.667117499999998,
"p95_ms": 3.9196679999999993,
"population_std_ms": 0.1767424054840424
},
"other": {
"mean_ms": 0.025222642857142857,
"n": 14,
"p50_ms": 0.025185,
"p95_ms": 0.025983,
"population_std_ms": 0.00032333101286073835
},
"output_head": {
"mean_ms": 0.08808714285714285,
"n": 14,
"p50_ms": 0.08807999999999999,
"p95_ms": 0.08870399999999999,
"population_std_ms": 0.0003292721100381563
},
"router": {
"mean_ms": 0.19489707142857132,
"n": 14,
"p50_ms": 0.19094449999999988,
"p95_ms": 0.23763299999999998,
"population_std_ms": 0.012033189735443558
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_6(6)": 14,
"execute_context_2(2049)_generation_4(4)": 1,
"execute_context_4(8191)_generation_1(1)": 1
},
"execute_wall": {
"mean_ms": 6.569652285714286,
"n": 14,
"p50_ms": 6.5619125,
"p95_ms": 6.809498,
"population_std_ms": 0.16639578247764245
},
"gpu_kernel_busy": {
"mean_ms": 6.461549142857142,
"n": 14,
"p50_ms": 6.452550999999998,
"p95_ms": 6.705629999999999,
"population_std_ms": 0.166627622430915
},
"non_kernel_gap": {
"mean_ms": 0.10810314285714392,
"n": 14,
"p50_ms": 0.10853050000000275,
"p95_ms": 0.1127690000000019,
"population_std_ms": 0.0025825165428091904
},
"selected_execute_annotation": "execute_context_0(0)_generation_6(6)",
"steps": 14,
"trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp2-b6-r1-20260723-20260723T091712228992Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b6-r1/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784798447891492657.pt.trace.json.gz"
},
{
"components": {
"attention": {
"mean_ms": 1.0614607142857144,
"n": 14,
"p50_ms": 1.0611505000000003,
"p95_ms": 1.0646370000000003,
"population_std_ms": 0.0017739766639056317
},
"collective": {
"mean_ms": 0.47087285714285715,
"n": 14,
"p50_ms": 0.46880499999999997,
"p95_ms": 0.48576,
"population_std_ms": 0.005842167135296126
},
"linear_norm_rope": {
"mean_ms": 0.9327132857142855,
"n": 14,
"p50_ms": 0.9321509999999997,
"p95_ms": 0.9383449999999995,
"population_std_ms": 0.002275944997721476
},
"moe": {
"mean_ms": 3.6822239285714278,
"n": 14,
"p50_ms": 3.6781699999999997,
"p95_ms": 3.9217039999999996,
"population_std_ms": 0.17642357594982436
},
"other": {
"mean_ms": 0.025353000000000004,
"n": 14,
"p50_ms": 0.02536,
"p95_ms": 0.026433,
"population_std_ms": 0.0005135631829260575
},
"output_head": {
"mean_ms": 0.08793421428571428,
"n": 14,
"p50_ms": 0.0880325,
"p95_ms": 0.088833,
"population_std_ms": 0.0005008674159569053
},
"router": {
"mean_ms": 0.2021904999999999,
"n": 14,
"p50_ms": 0.1997179999999999,
"p95_ms": 0.237536,
"population_std_ms": 0.009894411602732434
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_6(6)": 14,
"execute_context_2(2049)_generation_4(4)": 1,
"execute_context_4(8191)_generation_1(1)": 1
},
"execute_wall": {
"mean_ms": 6.570553642857143,
"n": 14,
"p50_ms": 6.5663730000000005,
"p95_ms": 6.809703000000001,
"population_std_ms": 0.16604228180350736
},
"gpu_kernel_busy": {
"mean_ms": 6.462748499999998,
"n": 14,
"p50_ms": 6.456941499999999,
"p95_ms": 6.703455999999998,
"population_std_ms": 0.16541565407168776
},
"non_kernel_gap": {
"mean_ms": 0.10780514285714433,
"n": 14,
"p50_ms": 0.10772100000000107,
"p95_ms": 0.1121450000000026,
"population_std_ms": 0.0019970330441916122
},
"selected_execute_annotation": "execute_context_0(0)_generation_6(6)",
"steps": 14,
"trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp2-b6-r1-20260723-20260723T091712228992Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b6-r1/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784798447895471197.pt.trace.json.gz"
}
],
"schema": "frontier-decode-batch-trace.v1"
}

View File

@@ -0,0 +1,191 @@
{
"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-b6-r2",
"rank_summary": {
"component_rank_mean_ms": {
"attention": 1.0463109615384618,
"collective": 0.48337815384615385,
"linear_norm_rope": 0.929004346153846,
"moe": 3.7078099230769217,
"other": 0.025587923076923078,
"output_head": 0.08800392307692309,
"router": 0.19478769230769236
},
"ranks": 2,
"slowest_rank_execute_mean_ms": 6.9378406923076925,
"slowest_rank_kernel_busy_mean_ms": 6.477923153846153
},
"ranks": [
{
"components": {
"attention": {
"mean_ms": 1.0448520000000003,
"n": 13,
"p50_ms": 1.045254000000001,
"p95_ms": 1.0465970000000002,
"population_std_ms": 0.0012648827856913572
},
"collective": {
"mean_ms": 0.4906066923076923,
"n": 13,
"p50_ms": 0.48854500000000006,
"p95_ms": 0.5128349999999999,
"population_std_ms": 0.007319711768018179
},
"linear_norm_rope": {
"mean_ms": 0.9276054615384616,
"n": 13,
"p50_ms": 0.927922,
"p95_ms": 0.9300229999999996,
"population_std_ms": 0.0012124997456231853
},
"moe": {
"mean_ms": 3.7032171538461522,
"n": 13,
"p50_ms": 3.6941509999999984,
"p95_ms": 3.9345319999999977,
"population_std_ms": 0.18506379688215108
},
"other": {
"mean_ms": 0.02531215384615385,
"n": 13,
"p50_ms": 0.025345,
"p95_ms": 0.025984,
"population_std_ms": 0.0003609239950148982
},
"output_head": {
"mean_ms": 0.08801007692307693,
"n": 13,
"p50_ms": 0.087968,
"p95_ms": 0.08851200000000001,
"population_std_ms": 0.0003446964018777317
},
"router": {
"mean_ms": 0.19831961538461543,
"n": 13,
"p50_ms": 0.1956510000000001,
"p95_ms": 0.23433300000000007,
"population_std_ms": 0.010532589860037432
}
},
"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": 6.937815615384616,
"n": 13,
"p50_ms": 6.920955,
"p95_ms": 7.177563,
"population_std_ms": 0.17465452547487034
},
"gpu_kernel_busy": {
"mean_ms": 6.477923153846153,
"n": 13,
"p50_ms": 6.464021999999998,
"p95_ms": 6.714968999999998,
"population_std_ms": 0.17390358211193135
},
"non_kernel_gap": {
"mean_ms": 0.4598924615384625,
"n": 13,
"p50_ms": 0.46010100000000165,
"p95_ms": 0.4628480000000019,
"population_std_ms": 0.0022957863280165477
},
"selected_execute_annotation": "execute_context_0(0)_generation_6(6)",
"steps": 13,
"trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp2-b6-r2-20260723-20260723T093020293408Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b6-r2/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784799236964172371.pt.trace.json.gz"
},
{
"components": {
"attention": {
"mean_ms": 1.0477699230769233,
"n": 13,
"p50_ms": 1.0473580000000002,
"p95_ms": 1.0502500000000003,
"population_std_ms": 0.0016845846994043283
},
"collective": {
"mean_ms": 0.47614961538461537,
"n": 13,
"p50_ms": 0.47488799999999987,
"p95_ms": 0.4852860000000001,
"population_std_ms": 0.006279926721013708
},
"linear_norm_rope": {
"mean_ms": 0.9304032307692304,
"n": 13,
"p50_ms": 0.9300610000000001,
"p95_ms": 0.9343409999999996,
"population_std_ms": 0.0015794439213190966
},
"moe": {
"mean_ms": 3.712402692307691,
"n": 13,
"p50_ms": 3.7038869999999973,
"p95_ms": 3.951868000000003,
"population_std_ms": 0.18554981438267218
},
"other": {
"mean_ms": 0.02586369230769231,
"n": 13,
"p50_ms": 0.025888,
"p95_ms": 0.026400000000000003,
"population_std_ms": 0.0002951522122606689
},
"output_head": {
"mean_ms": 0.08799776923076924,
"n": 13,
"p50_ms": 0.087937,
"p95_ms": 0.088992,
"population_std_ms": 0.00042456876834413246
},
"router": {
"mean_ms": 0.19125576923076928,
"n": 13,
"p50_ms": 0.18793900000000005,
"p95_ms": 0.23312300000000005,
"population_std_ms": 0.012158267147240543
}
},
"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": 6.9378406923076925,
"n": 13,
"p50_ms": 6.920646,
"p95_ms": 7.1769359999999995,
"population_std_ms": 0.17404824161814114
},
"gpu_kernel_busy": {
"mean_ms": 6.471842692307691,
"n": 13,
"p50_ms": 6.4540469999999965,
"p95_ms": 6.708258000000003,
"population_std_ms": 0.17518788350506015
},
"non_kernel_gap": {
"mean_ms": 0.465998000000001,
"n": 13,
"p50_ms": 0.4667860000000026,
"p95_ms": 0.4705280000000025,
"population_std_ms": 0.0037250578518997
},
"selected_execute_annotation": "execute_context_0(0)_generation_6(6)",
"steps": 13,
"trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp2-b6-r2-20260723-20260723T093020293408Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b6-r2/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784799236965538368.pt.trace.json.gz"
}
],
"schema": "frontier-decode-batch-trace.v1"
}

View File

@@ -0,0 +1,191 @@
{
"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-b8-r1",
"rank_summary": {
"component_rank_mean_ms": {
"attention": 1.4162915000000003,
"collective": 0.5046254615384616,
"linear_norm_rope": 0.933206192307692,
"moe": 2.681186538461537,
"other": 0.023443884615384616,
"output_head": 0.08826711538461537,
"router": 0.19981553846153838
},
"ranks": 2,
"slowest_rank_execute_mean_ms": 5.967337846153845,
"slowest_rank_kernel_busy_mean_ms": 5.849403615384613
},
"ranks": [
{
"components": {
"attention": {
"mean_ms": 1.4268944615384618,
"n": 13,
"p50_ms": 1.4273899999999997,
"p95_ms": 1.4289299999999996,
"population_std_ms": 0.0013227596802130133
},
"collective": {
"mean_ms": 0.4871666153846154,
"n": 13,
"p50_ms": 0.4847079999999998,
"p95_ms": 0.5161030000000001,
"population_std_ms": 0.009071831835526453
},
"linear_norm_rope": {
"mean_ms": 0.9357503846153842,
"n": 13,
"p50_ms": 0.9351129999999993,
"p95_ms": 0.9375759999999999,
"population_std_ms": 0.0012191190727774577
},
"moe": {
"mean_ms": 2.6808982307692295,
"n": 13,
"p50_ms": 2.729251,
"p95_ms": 2.8241379999999983,
"population_std_ms": 0.11820978926868417
},
"other": {
"mean_ms": 0.023988000000000002,
"n": 13,
"p50_ms": 0.023935,
"p95_ms": 0.024639999999999995,
"population_std_ms": 0.0002731643630321658
},
"output_head": {
"mean_ms": 0.08829546153846153,
"n": 13,
"p50_ms": 0.088256,
"p95_ms": 0.08921599999999999,
"population_std_ms": 0.00048060836693389233
},
"router": {
"mean_ms": 0.2012756923076922,
"n": 13,
"p50_ms": 0.20156699999999994,
"p95_ms": 0.20582599999999993,
"population_std_ms": 0.0022949889352713113
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_8(8)": 13,
"execute_context_1(2048)_generation_1(1)": 1,
"execute_context_3(4098)_generation_5(5)": 1,
"execute_context_4(8190)_generation_2(2)": 1
},
"execute_wall": {
"mean_ms": 5.966980846153846,
"n": 13,
"p50_ms": 6.004943,
"p95_ms": 6.112047,
"population_std_ms": 0.11913819132925879
},
"gpu_kernel_busy": {
"mean_ms": 5.844268846153844,
"n": 13,
"p50_ms": 5.885293999999999,
"p95_ms": 5.987602999999998,
"population_std_ms": 0.11849233575983938
},
"non_kernel_gap": {
"mean_ms": 0.12271200000000157,
"n": 13,
"p50_ms": 0.12307100000000126,
"p95_ms": 0.12728500000000142,
"population_std_ms": 0.0027851573357023283
},
"selected_execute_annotation": "execute_context_0(0)_generation_8(8)",
"steps": 13,
"trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp2-b8-r1-20260723-20260723T091715999468Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b8-r1/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784798455024962606.pt.trace.json.gz"
},
{
"components": {
"attention": {
"mean_ms": 1.405688538461539,
"n": 13,
"p50_ms": 1.4057520000000006,
"p95_ms": 1.4114940000000005,
"population_std_ms": 0.0022431369386294517
},
"collective": {
"mean_ms": 0.5220843076923077,
"n": 13,
"p50_ms": 0.5193970000000001,
"p95_ms": 0.5542680000000001,
"population_std_ms": 0.010336781774023671
},
"linear_norm_rope": {
"mean_ms": 0.9306619999999997,
"n": 13,
"p50_ms": 0.9303679999999996,
"p95_ms": 0.9333509999999994,
"population_std_ms": 0.0014067406955851874
},
"moe": {
"mean_ms": 2.6814748461538445,
"n": 13,
"p50_ms": 2.7311729999999965,
"p95_ms": 2.8229829999999962,
"population_std_ms": 0.11917174241136594
},
"other": {
"mean_ms": 0.02289976923076923,
"n": 13,
"p50_ms": 0.022943999999999996,
"p95_ms": 0.02352,
"population_std_ms": 0.0002890651121343674
},
"output_head": {
"mean_ms": 0.08823876923076922,
"n": 13,
"p50_ms": 0.088193,
"p95_ms": 0.088768,
"population_std_ms": 0.0003492319383240336
},
"router": {
"mean_ms": 0.19835538461538452,
"n": 13,
"p50_ms": 0.1982099999999999,
"p95_ms": 0.2010899999999999,
"population_std_ms": 0.0022037652233764197
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_8(8)": 13,
"execute_context_1(2048)_generation_1(1)": 1,
"execute_context_3(4098)_generation_5(5)": 1,
"execute_context_4(8190)_generation_2(2)": 1
},
"execute_wall": {
"mean_ms": 5.967337846153845,
"n": 13,
"p50_ms": 6.0104049999999996,
"p95_ms": 6.1097969999999995,
"population_std_ms": 0.11987574925913026
},
"gpu_kernel_busy": {
"mean_ms": 5.849403615384613,
"n": 13,
"p50_ms": 5.889734999999996,
"p95_ms": 5.993167999999996,
"population_std_ms": 0.11980136802451119
},
"non_kernel_gap": {
"mean_ms": 0.11793423076923243,
"n": 13,
"p50_ms": 0.11715500000000123,
"p95_ms": 0.12245800000000262,
"population_std_ms": 0.002861606035183301
},
"selected_execute_annotation": "execute_context_0(0)_generation_8(8)",
"steps": 13,
"trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp2-b8-r1-20260723-20260723T091715999468Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b8-r1/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784798455030360286.pt.trace.json.gz"
}
],
"schema": "frontier-decode-batch-trace.v1"
}

View File

@@ -0,0 +1,191 @@
{
"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-b8-r2",
"rank_summary": {
"component_rank_mean_ms": {
"attention": 1.400657307692308,
"collective": 0.5005616923076923,
"linear_norm_rope": 0.9316651538461536,
"moe": 2.69281696153846,
"other": 0.023672576923076925,
"output_head": 0.08830773076923076,
"router": 0.1908271153846154
},
"ranks": 2,
"slowest_rank_execute_mean_ms": 6.309095692307692,
"slowest_rank_kernel_busy_mean_ms": 5.828548538461537
},
"ranks": [
{
"components": {
"attention": {
"mean_ms": 1.4095765384615386,
"n": 13,
"p50_ms": 1.4091810000000007,
"p95_ms": 1.4131269999999998,
"population_std_ms": 0.0017758118236840018
},
"collective": {
"mean_ms": 0.4864672307692308,
"n": 13,
"p50_ms": 0.4871060000000002,
"p95_ms": 0.5083250000000001,
"population_std_ms": 0.007854287590999577
},
"linear_norm_rope": {
"mean_ms": 0.9326894615384612,
"n": 13,
"p50_ms": 0.9327419999999998,
"p95_ms": 0.9343809999999997,
"population_std_ms": 0.001099693356936376
},
"moe": {
"mean_ms": 2.692551615384614,
"n": 13,
"p50_ms": 2.7793569999999983,
"p95_ms": 2.871725999999997,
"population_std_ms": 0.17050402067063422
},
"other": {
"mean_ms": 0.024125384615384618,
"n": 13,
"p50_ms": 0.024064000000000002,
"p95_ms": 0.024864000000000008,
"population_std_ms": 0.00029315092948108124
},
"output_head": {
"mean_ms": 0.08821176923076922,
"n": 13,
"p50_ms": 0.08828799999999999,
"p95_ms": 0.088672,
"population_std_ms": 0.0004720397887150791
},
"router": {
"mean_ms": 0.19492653846153846,
"n": 13,
"p50_ms": 0.19584,
"p95_ms": 0.19798399999999997,
"population_std_ms": 0.002327761308652399
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_8(8)": 13,
"execute_context_2(2051)_generation_6(6)": 1,
"execute_context_2(4096)_generation_1(1)": 1,
"execute_context_4(8189)_generation_3(3)": 1
},
"execute_wall": {
"mean_ms": 6.309095692307692,
"n": 13,
"p50_ms": 6.398511,
"p95_ms": 6.483886999999999,
"population_std_ms": 0.1703797844741088
},
"gpu_kernel_busy": {
"mean_ms": 5.828548538461537,
"n": 13,
"p50_ms": 5.915967999999998,
"p95_ms": 6.002267999999997,
"population_std_ms": 0.17012899737805992
},
"non_kernel_gap": {
"mean_ms": 0.4805471538461554,
"n": 13,
"p50_ms": 0.4803160000000002,
"p95_ms": 0.4859510000000009,
"population_std_ms": 0.0025392862972511096
},
"selected_execute_annotation": "execute_context_0(0)_generation_8(8)",
"steps": 13,
"trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp2-b8-r2-20260723-20260723T093023994242Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b8-r2/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784799245841164026.pt.trace.json.gz"
},
{
"components": {
"attention": {
"mean_ms": 1.3917380769230774,
"n": 13,
"p50_ms": 1.3920280000000005,
"p95_ms": 1.3950360000000008,
"population_std_ms": 0.001887833412693738
},
"collective": {
"mean_ms": 0.5146561538461538,
"n": 13,
"p50_ms": 0.5156739999999999,
"p95_ms": 0.5248290000000001,
"population_std_ms": 0.00624208518964558
},
"linear_norm_rope": {
"mean_ms": 0.9306408461538459,
"n": 13,
"p50_ms": 0.9303399999999994,
"p95_ms": 0.9336909999999994,
"population_std_ms": 0.0015690834093706387
},
"moe": {
"mean_ms": 2.693082307692306,
"n": 13,
"p50_ms": 2.778146,
"p95_ms": 2.867843999999997,
"population_std_ms": 0.17102703603069247
},
"other": {
"mean_ms": 0.02321976923076923,
"n": 13,
"p50_ms": 0.023139,
"p95_ms": 0.023648000000000002,
"population_std_ms": 0.00028077369859458957
},
"output_head": {
"mean_ms": 0.08840369230769231,
"n": 13,
"p50_ms": 0.08832,
"p95_ms": 0.089408,
"population_std_ms": 0.0004100955582104095
},
"router": {
"mean_ms": 0.18672769230769232,
"n": 13,
"p50_ms": 0.18675,
"p95_ms": 0.189218,
"population_std_ms": 0.0011293141134617489
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_8(8)": 13,
"execute_context_2(2051)_generation_6(6)": 1,
"execute_context_2(4096)_generation_1(1)": 1,
"execute_context_4(8189)_generation_3(3)": 1
},
"execute_wall": {
"mean_ms": 6.307694615384615,
"n": 13,
"p50_ms": 6.399717,
"p95_ms": 6.488933,
"population_std_ms": 0.17066632055317688
},
"gpu_kernel_busy": {
"mean_ms": 5.828468538461537,
"n": 13,
"p50_ms": 5.9137319999999995,
"p95_ms": 6.007808999999997,
"population_std_ms": 0.17195541813398352
},
"non_kernel_gap": {
"mean_ms": 0.4792260769230788,
"n": 13,
"p50_ms": 0.4783710000000063,
"p95_ms": 0.4893030000000005,
"population_std_ms": 0.00435339587097986
},
"selected_execute_annotation": "execute_context_0(0)_generation_8(8)",
"steps": 13,
"trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp2-b8-r2-20260723-20260723T093023994242Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b8-r2/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784799245841819751.pt.trace.json.gz"
}
],
"schema": "frontier-decode-batch-trace.v1"
}

View File

@@ -0,0 +1,353 @@
{
"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-r1",
"rank_summary": {
"component_rank_mean_ms": {
"attention": 0.8023426607142858,
"collective": 0.5361581428571428,
"linear_norm_rope": 0.8392915178571427,
"moe": 1.9595749285714295,
"other": 0.021800214285714284,
"output_head": 0.04583946428571428,
"router": 0.1894944999999999
},
"ranks": 4,
"slowest_rank_execute_mean_ms": 4.516427428571428,
"slowest_rank_kernel_busy_mean_ms": 4.397215785714287
},
"ranks": [
{
"components": {
"attention": {
"mean_ms": 0.8026924285714286,
"n": 14,
"p50_ms": 0.8022965,
"p95_ms": 0.810657,
"population_std_ms": 0.004568636975764919
},
"collective": {
"mean_ms": 0.5177565714285713,
"n": 14,
"p50_ms": 0.5184174999999998,
"p95_ms": 0.5240059999999997,
"population_std_ms": 0.0039342607349554136
},
"linear_norm_rope": {
"mean_ms": 0.8483352857142855,
"n": 14,
"p50_ms": 0.8486384999999999,
"p95_ms": 0.8519969999999999,
"population_std_ms": 0.0017219747562680734
},
"moe": {
"mean_ms": 1.9629181428571427,
"n": 14,
"p50_ms": 1.9689039999999998,
"p95_ms": 2.131421,
"population_std_ms": 0.11758295795361873
},
"other": {
"mean_ms": 0.022141571428571427,
"n": 14,
"p50_ms": 0.022127,
"p95_ms": 0.022622999999999997,
"population_std_ms": 0.00024374275499436835
},
"output_head": {
"mean_ms": 0.045906214285714286,
"n": 14,
"p50_ms": 0.045871999999999996,
"p95_ms": 0.046592,
"population_std_ms": 0.00048383456124285047
},
"router": {
"mean_ms": 0.18891014285714272,
"n": 14,
"p50_ms": 0.18883199999999986,
"p95_ms": 0.18931099999999992,
"population_std_ms": 0.00019712608624317712
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_1(1)": 1,
"execute_context_0(0)_generation_4(4)": 14,
"execute_context_3(6144)_generation_1(1)": 1
},
"execute_wall": {
"mean_ms": 4.515594,
"n": 14,
"p50_ms": 4.512055999999999,
"p95_ms": 4.8260879999999995,
"population_std_ms": 0.14829775976248402
},
"gpu_kernel_busy": {
"mean_ms": 4.388660357142856,
"n": 14,
"p50_ms": 4.3929335,
"p95_ms": 4.560478,
"population_std_ms": 0.12189088321563175
},
"non_kernel_gap": {
"mean_ms": 0.12693364285714326,
"n": 14,
"p50_ms": 0.10895650000000145,
"p95_ms": 0.3681599999999996,
"population_std_ms": 0.06698859556415654
},
"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-r1-20260723-20260723T091059346688Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b4-r1/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784798099190414139.pt.trace.json.gz"
},
{
"components": {
"attention": {
"mean_ms": 0.7969025714285717,
"n": 14,
"p50_ms": 0.7975640000000002,
"p95_ms": 0.803777,
"population_std_ms": 0.004672418671833448
},
"collective": {
"mean_ms": 0.5435259285714286,
"n": 14,
"p50_ms": 0.5245414999999998,
"p95_ms": 0.7792909999999997,
"population_std_ms": 0.0654428389790491
},
"linear_norm_rope": {
"mean_ms": 0.8351954285714284,
"n": 14,
"p50_ms": 0.8352339999999999,
"p95_ms": 0.8379900000000003,
"population_std_ms": 0.0011727439566058622
},
"moe": {
"mean_ms": 1.9629085714285726,
"n": 14,
"p50_ms": 1.9686130000000002,
"p95_ms": 2.1275570000000004,
"population_std_ms": 0.11811909377144619
},
"other": {
"mean_ms": 0.02171192857142857,
"n": 14,
"p50_ms": 0.021582999999999998,
"p95_ms": 0.023136000000000004,
"population_std_ms": 0.0004568249843501685
},
"output_head": {
"mean_ms": 0.04598635714285714,
"n": 14,
"p50_ms": 0.0461605,
"p95_ms": 0.046688,
"population_std_ms": 0.00048825660805167076
},
"router": {
"mean_ms": 0.18940242857142844,
"n": 14,
"p50_ms": 0.18939349999999988,
"p95_ms": 0.19011299999999992,
"population_std_ms": 0.0003183344409996063
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_1(1)": 1,
"execute_context_0(0)_generation_4(4)": 14,
"execute_context_3(6144)_generation_1(1)": 1
},
"execute_wall": {
"mean_ms": 4.515569785714286,
"n": 14,
"p50_ms": 4.509453000000001,
"p95_ms": 4.822798,
"population_std_ms": 0.1475542723441973
},
"gpu_kernel_busy": {
"mean_ms": 4.3956332142857155,
"n": 14,
"p50_ms": 4.3885055,
"p95_ms": 4.704691000000001,
"population_std_ms": 0.1480161569835144
},
"non_kernel_gap": {
"mean_ms": 0.11993657142857048,
"n": 14,
"p50_ms": 0.12018349999999911,
"p95_ms": 0.12278300000000009,
"population_std_ms": 0.0023027362206822326
},
"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-r1-20260723-20260723T091059346688Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b4-r1/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784798099190728578.pt.trace.json.gz"
},
{
"components": {
"attention": {
"mean_ms": 0.8076340714285717,
"n": 14,
"p50_ms": 0.8078890000000003,
"p95_ms": 0.811872,
"population_std_ms": 0.003509697513711885
},
"collective": {
"mean_ms": 0.538438357142857,
"n": 14,
"p50_ms": 0.5197394999999998,
"p95_ms": 0.7775990000000002,
"population_std_ms": 0.06647859896624862
},
"linear_norm_rope": {
"mean_ms": 0.8366736428571427,
"n": 14,
"p50_ms": 0.8371874999999998,
"p95_ms": 0.8391049999999995,
"population_std_ms": 0.002070122274067762
},
"moe": {
"mean_ms": 1.9572025000000013,
"n": 14,
"p50_ms": 1.9622045000000017,
"p95_ms": 2.1186610000000012,
"population_std_ms": 0.11785303854665174
},
"other": {
"mean_ms": 0.021651357142857146,
"n": 14,
"p50_ms": 0.0216015,
"p95_ms": 0.022528000000000003,
"population_std_ms": 0.0003619630224095226
},
"output_head": {
"mean_ms": 0.04572821428571428,
"n": 14,
"p50_ms": 0.045616000000000004,
"p95_ms": 0.046816,
"population_std_ms": 0.0004743333936877599
},
"router": {
"mean_ms": 0.18988764285714277,
"n": 14,
"p50_ms": 0.1899184999999999,
"p95_ms": 0.1904639999999999,
"population_std_ms": 0.00036004535570296044
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_1(1)": 1,
"execute_context_0(0)_generation_4(4)": 14,
"execute_context_3(6144)_generation_1(1)": 1
},
"execute_wall": {
"mean_ms": 4.516208928571428,
"n": 14,
"p50_ms": 4.5094615000000005,
"p95_ms": 4.827749,
"population_std_ms": 0.14783990641591432
},
"gpu_kernel_busy": {
"mean_ms": 4.397215785714287,
"n": 14,
"p50_ms": 4.391749500000001,
"p95_ms": 4.706615000000002,
"population_std_ms": 0.14841367943313954
},
"non_kernel_gap": {
"mean_ms": 0.11899314285714155,
"n": 14,
"p50_ms": 0.11911499999999897,
"p95_ms": 0.12231999999999754,
"population_std_ms": 0.0022138607149742996
},
"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-r1-20260723-20260723T091059346688Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b4-r1/traces/profile/dp0_pp0_tp2_dcp0_ep2_rank2.1784798099190414025.pt.trace.json.gz"
},
{
"components": {
"attention": {
"mean_ms": 0.8021415714285716,
"n": 14,
"p50_ms": 0.8019065000000002,
"p95_ms": 0.8102380000000002,
"population_std_ms": 0.004568393789542204
},
"collective": {
"mean_ms": 0.5449117142857143,
"n": 14,
"p50_ms": 0.5278735,
"p95_ms": 0.781215,
"population_std_ms": 0.0655966698484312
},
"linear_norm_rope": {
"mean_ms": 0.8369617142857141,
"n": 14,
"p50_ms": 0.8372430000000001,
"p95_ms": 0.8394259999999998,
"population_std_ms": 0.0013668606590375937
},
"moe": {
"mean_ms": 1.9552705000000008,
"n": 14,
"p50_ms": 1.9632605,
"p95_ms": 2.1177540000000006,
"population_std_ms": 0.11724808995809416
},
"other": {
"mean_ms": 0.021696,
"n": 14,
"p50_ms": 0.021648,
"p95_ms": 0.02288,
"population_std_ms": 0.0004689002330682176
},
"output_head": {
"mean_ms": 0.045737071428571426,
"n": 14,
"p50_ms": 0.0457755,
"p95_ms": 0.046496,
"population_std_ms": 0.00039792039122807263
},
"router": {
"mean_ms": 0.18977778571428564,
"n": 14,
"p50_ms": 0.1896624999999999,
"p95_ms": 0.1909739999999999,
"population_std_ms": 0.00041644501927821606
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_1(1)": 1,
"execute_context_0(0)_generation_4(4)": 14,
"execute_context_3(6144)_generation_1(1)": 1
},
"execute_wall": {
"mean_ms": 4.516427428571428,
"n": 14,
"p50_ms": 4.508496,
"p95_ms": 4.82816,
"population_std_ms": 0.14821148953231575
},
"gpu_kernel_busy": {
"mean_ms": 4.3964963571428575,
"n": 14,
"p50_ms": 4.3874035,
"p95_ms": 4.705174,
"population_std_ms": 0.14715990628788167
},
"non_kernel_gap": {
"mean_ms": 0.11993107142857092,
"n": 14,
"p50_ms": 0.11941749999999951,
"p95_ms": 0.1248560000000003,
"population_std_ms": 0.002664138817283219
},
"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-r1-20260723-20260723T091059346688Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b4-r1/traces/profile/dp0_pp0_tp3_dcp0_ep3_rank3.1784798099191829059.pt.trace.json.gz"
}
],
"schema": "frontier-decode-batch-trace.v1"
}

View File

@@ -0,0 +1,353 @@
{
"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"
}

View File

@@ -0,0 +1,357 @@
{
"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"
}

View File

@@ -0,0 +1,353 @@
{
"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-r2",
"rank_summary": {
"component_rank_mean_ms": {
"attention": 0.9215755535714284,
"collective": 4.099890464285714,
"linear_norm_rope": 0.8376546964285715,
"moe": 2.383938624999999,
"other": 0.02548019642857143,
"output_head": 0.04836294642857143,
"router": 0.19243757142857137
},
"ranks": 4,
"slowest_rank_execute_mean_ms": 10.1569875,
"slowest_rank_kernel_busy_mean_ms": 9.689807857142856
},
"ranks": [
{
"components": {
"attention": {
"mean_ms": 0.9138666428571425,
"n": 14,
"p50_ms": 0.9139704999999996,
"p95_ms": 0.9164179999999996,
"population_std_ms": 0.0016477326242507631
},
"collective": {
"mean_ms": 5.290839214285713,
"n": 14,
"p50_ms": 0.5740495000000001,
"p95_ms": 28.996437999999984,
"population_std_ms": 9.010484784994565
},
"linear_norm_rope": {
"mean_ms": 0.8356119285714287,
"n": 14,
"p50_ms": 0.8351870000000001,
"p95_ms": 0.8384630000000003,
"population_std_ms": 0.0012410830215286587
},
"moe": {
"mean_ms": 2.382082642857142,
"n": 14,
"p50_ms": 2.368174999999999,
"p95_ms": 2.4507140000000005,
"population_std_ms": 0.04469279722346926
},
"other": {
"mean_ms": 0.025481714285714285,
"n": 14,
"p50_ms": 0.025521000000000002,
"p95_ms": 0.025824,
"population_std_ms": 0.00017456289434365226
},
"output_head": {
"mean_ms": 0.048274285714285714,
"n": 14,
"p50_ms": 0.048175499999999996,
"p95_ms": 0.048896,
"population_std_ms": 0.0003860829719431935
},
"router": {
"mean_ms": 0.19008764285714277,
"n": 14,
"p50_ms": 0.19016149999999996,
"p95_ms": 0.1924179999999999,
"population_std_ms": 0.001319140120746566
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_6(6)": 14,
"execute_context_2(4096)_generation_4(4)": 1,
"execute_context_3(6144)_generation_1(1)": 1
},
"execute_wall": {
"mean_ms": 10.1569875,
"n": 14,
"p50_ms": 5.495552,
"p95_ms": 33.916852,
"population_std_ms": 9.023692546910278
},
"gpu_kernel_busy": {
"mean_ms": 9.68624407142857,
"n": 14,
"p50_ms": 5.0233855,
"p95_ms": 33.44527299999998,
"population_std_ms": 9.023394784605482
},
"non_kernel_gap": {
"mean_ms": 0.4707434285714301,
"n": 14,
"p50_ms": 0.47161650000001076,
"p95_ms": 0.47796200000000066,
"population_std_ms": 0.004213033072914231
},
"selected_execute_annotation": "execute_context_0(0)_generation_6(6)",
"steps": 14,
"trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b6-r2-20260723-20260723T092332531885Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b6-r2/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784798836346445272.pt.trace.json.gz"
},
{
"components": {
"attention": {
"mean_ms": 0.9236260714285712,
"n": 14,
"p50_ms": 0.9236309999999999,
"p95_ms": 0.9261099999999999,
"population_std_ms": 0.0016452857964623058
},
"collective": {
"mean_ms": 5.292963285714286,
"n": 14,
"p50_ms": 0.5790519999999999,
"p95_ms": 28.995478000000002,
"population_std_ms": 9.00940907489549
},
"linear_norm_rope": {
"mean_ms": 0.8306526428571429,
"n": 14,
"p50_ms": 0.8308655000000003,
"p95_ms": 0.8323229999999998,
"population_std_ms": 0.001215001387838325
},
"moe": {
"mean_ms": 2.372463214285713,
"n": 14,
"p50_ms": 2.3604929999999986,
"p95_ms": 2.4334759999999993,
"population_std_ms": 0.04456007217899188
},
"other": {
"mean_ms": 0.025364571428571427,
"n": 14,
"p50_ms": 0.025328499999999997,
"p95_ms": 0.025759999999999998,
"population_std_ms": 0.00018273154168487357
},
"output_head": {
"mean_ms": 0.04847557142857143,
"n": 14,
"p50_ms": 0.048352,
"p95_ms": 0.049377000000000004,
"population_std_ms": 0.00036324720317195205
},
"router": {
"mean_ms": 0.1902149285714285,
"n": 14,
"p50_ms": 0.1895669999999999,
"p95_ms": 0.19510299999999997,
"population_std_ms": 0.002332658767044482
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_6(6)": 14,
"execute_context_2(4096)_generation_4(4)": 1,
"execute_context_3(6144)_generation_1(1)": 1
},
"execute_wall": {
"mean_ms": 10.156081571428572,
"n": 14,
"p50_ms": 5.49357,
"p95_ms": 33.919204,
"population_std_ms": 9.024698774226101
},
"gpu_kernel_busy": {
"mean_ms": 9.683760285714284,
"n": 14,
"p50_ms": 5.019874,
"p95_ms": 33.448195,
"population_std_ms": 9.025241580098282
},
"non_kernel_gap": {
"mean_ms": 0.47232128571428716,
"n": 14,
"p50_ms": 0.47191050000000256,
"p95_ms": 0.47722900000000035,
"population_std_ms": 0.002093886660480702
},
"selected_execute_annotation": "execute_context_0(0)_generation_6(6)",
"steps": 14,
"trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b6-r2-20260723-20260723T092332531885Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b6-r2/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784798836333019388.pt.trace.json.gz"
},
{
"components": {
"attention": {
"mean_ms": 0.9213676428571428,
"n": 14,
"p50_ms": 0.921938,
"p95_ms": 0.9297530000000004,
"population_std_ms": 0.004745679668425435
},
"collective": {
"mean_ms": 5.281759785714286,
"n": 14,
"p50_ms": 0.5755820000000003,
"p95_ms": 28.99219900000001,
"population_std_ms": 9.010812440241091
},
"linear_norm_rope": {
"mean_ms": 0.840441214285714,
"n": 14,
"p50_ms": 0.8404519999999995,
"p95_ms": 0.8441329999999994,
"population_std_ms": 0.0019087839501543548
},
"moe": {
"mean_ms": 2.3862941428571425,
"n": 14,
"p50_ms": 2.373951,
"p95_ms": 2.459937000000001,
"population_std_ms": 0.04582171989953023
},
"other": {
"mean_ms": 0.025662357142857143,
"n": 14,
"p50_ms": 0.0256645,
"p95_ms": 0.026143999999999997,
"population_std_ms": 0.00029092699308610424
},
"output_head": {
"mean_ms": 0.048436714285714284,
"n": 14,
"p50_ms": 0.048575999999999994,
"p95_ms": 0.048991999999999994,
"population_std_ms": 0.0004154401157759286
},
"router": {
"mean_ms": 0.18584599999999996,
"n": 14,
"p50_ms": 0.185825,
"p95_ms": 0.18636899999999995,
"population_std_ms": 0.00029020731505990466
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_6(6)": 14,
"execute_context_2(4096)_generation_4(4)": 1,
"execute_context_3(6144)_generation_1(1)": 1
},
"execute_wall": {
"mean_ms": 10.156770214285714,
"n": 14,
"p50_ms": 5.493733,
"p95_ms": 33.916464999999995,
"population_std_ms": 9.023992692816982
},
"gpu_kernel_busy": {
"mean_ms": 9.689807857142856,
"n": 14,
"p50_ms": 5.033896,
"p95_ms": 33.45033900000001,
"population_std_ms": 9.02452540636983
},
"non_kernel_gap": {
"mean_ms": 0.4669623571428573,
"n": 14,
"p50_ms": 0.467391000000001,
"p95_ms": 0.47341499999999836,
"population_std_ms": 0.004137908505636468
},
"selected_execute_annotation": "execute_context_0(0)_generation_6(6)",
"steps": 14,
"trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b6-r2-20260723-20260723T092332531885Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b6-r2/traces/profile/dp0_pp0_tp2_dcp0_ep2_rank2.1784798836334934191.pt.trace.json.gz"
},
{
"components": {
"attention": {
"mean_ms": 0.9274418571428571,
"n": 14,
"p50_ms": 0.9274730000000002,
"p95_ms": 0.9312359999999998,
"population_std_ms": 0.0016344587071277954
},
"collective": {
"mean_ms": 0.5339995714285714,
"n": 14,
"p50_ms": 0.5353115,
"p95_ms": 0.5461410000000002,
"population_std_ms": 0.006859063864846362
},
"linear_norm_rope": {
"mean_ms": 0.8439130000000005,
"n": 14,
"p50_ms": 0.8440930000000004,
"p95_ms": 0.8451400000000011,
"population_std_ms": 0.000779706171763452
},
"moe": {
"mean_ms": 2.3949144999999987,
"n": 14,
"p50_ms": 2.386371499999999,
"p95_ms": 2.457828999999998,
"population_std_ms": 0.044398212431438724
},
"other": {
"mean_ms": 0.02541214285714286,
"n": 14,
"p50_ms": 0.0254395,
"p95_ms": 0.025761999999999997,
"population_std_ms": 0.00027587053307739895
},
"output_head": {
"mean_ms": 0.048265214285714286,
"n": 14,
"p50_ms": 0.048063999999999996,
"p95_ms": 0.049057,
"population_std_ms": 0.00045419413385081205
},
"router": {
"mean_ms": 0.20360171428571425,
"n": 14,
"p50_ms": 0.20369749999999998,
"p95_ms": 0.20981799999999995,
"population_std_ms": 0.0021429506170088787
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_6(6)": 14,
"execute_context_2(4096)_generation_4(4)": 1,
"execute_context_3(6144)_generation_1(1)": 1
},
"execute_wall": {
"mean_ms": 10.156985785714285,
"n": 14,
"p50_ms": 5.495433,
"p95_ms": 33.916939,
"population_std_ms": 9.023746050846789
},
"gpu_kernel_busy": {
"mean_ms": 4.977547999999999,
"n": 14,
"p50_ms": 4.961732999999999,
"p95_ms": 5.047107999999999,
"population_std_ms": 0.04773951894694539
},
"non_kernel_gap": {
"mean_ms": 5.179437785714287,
"n": 14,
"p50_ms": 0.4635420000000008,
"p95_ms": 28.877357,
"population_std_ms": 9.007091777202437
},
"selected_execute_annotation": "execute_context_0(0)_generation_6(6)",
"steps": 14,
"trace": "runs/frontier-decode-batch-grid-v0/fleet-artifacts/decode-grid-tp4-b6-r2-20260723-20260723T092332531885Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b6-r2/traces/profile/dp0_pp0_tp3_dcp0_ep3_rank3.1784798836405275119.pt.trace.json.gz"
}
],
"schema": "frontier-decode-batch-trace.v1"
}

View File

@@ -0,0 +1,357 @@
{
"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"
}

View File

@@ -0,0 +1,357 @@
{
"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-r2",
"rank_summary": {
"component_rank_mean_ms": {
"attention": 0.9134566730769228,
"collective": 0.5546497884615385,
"linear_norm_rope": 0.8387807692307689,
"moe": 2.0065153269230764,
"other": 0.02364873076923077,
"output_head": 0.04593917307692308,
"router": 0.19024988461538456
},
"ranks": 4,
"slowest_rank_execute_mean_ms": 5.046865153846154,
"slowest_rank_kernel_busy_mean_ms": 4.576482615384614
},
"ranks": [
{
"components": {
"attention": {
"mean_ms": 0.9168304615384618,
"n": 13,
"p50_ms": 0.9167360000000001,
"p95_ms": 0.9226820000000003,
"population_std_ms": 0.0042293902200123395
},
"collective": {
"mean_ms": 0.533513923076923,
"n": 13,
"p50_ms": 0.5343079999999998,
"p95_ms": 0.5469470000000001,
"population_std_ms": 0.005929160823506614
},
"linear_norm_rope": {
"mean_ms": 0.8429445384615385,
"n": 13,
"p50_ms": 0.8424360000000001,
"p95_ms": 0.8458869999999998,
"population_std_ms": 0.001745678030732511
},
"moe": {
"mean_ms": 2.013382153846152,
"n": 13,
"p50_ms": 1.9625909999999984,
"p95_ms": 2.195520999999998,
"population_std_ms": 0.13058695301059595
},
"other": {
"mean_ms": 0.023465076923076922,
"n": 13,
"p50_ms": 0.023581,
"p95_ms": 0.023903,
"population_std_ms": 0.00026946969618078375
},
"output_head": {
"mean_ms": 0.045974307692307696,
"n": 13,
"p50_ms": 0.046048,
"p95_ms": 0.046624000000000006,
"population_std_ms": 0.00041656145259371096
},
"router": {
"mean_ms": 0.2003721538461538,
"n": 13,
"p50_ms": 0.199709,
"p95_ms": 0.20480099999999998,
"population_std_ms": 0.002108014079873938
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_8(8)": 13,
"execute_context_1(4)_generation_7(7)": 1,
"execute_context_3(6144)_generation_1(1)": 1,
"execute_context_4(8188)_generation_4(4)": 1
},
"execute_wall": {
"mean_ms": 5.04529823076923,
"n": 13,
"p50_ms": 4.9983770000000005,
"p95_ms": 5.2427600000000005,
"population_std_ms": 0.1337420429024321
},
"gpu_kernel_busy": {
"mean_ms": 4.576482615384614,
"n": 13,
"p50_ms": 4.520321999999998,
"p95_ms": 4.770687999999998,
"population_std_ms": 0.13507694537418738
},
"non_kernel_gap": {
"mean_ms": 0.46881561538461686,
"n": 13,
"p50_ms": 0.46984200000000076,
"p95_ms": 0.4780550000000021,
"population_std_ms": 0.004066459044397948
},
"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-r2-20260723-20260723T093027863838Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b8-r2/traces/profile/dp0_pp0_tp0_dcp0_ep0_rank0.1784799265976107810.pt.trace.json.gz"
},
{
"components": {
"attention": {
"mean_ms": 0.9115253076923072,
"n": 13,
"p50_ms": 0.9091299999999993,
"p95_ms": 0.9181569999999997,
"population_std_ms": 0.004755129738335539
},
"collective": {
"mean_ms": 0.5619680769230769,
"n": 13,
"p50_ms": 0.5602239999999999,
"p95_ms": 0.5761279999999999,
"population_std_ms": 0.0068347860634070876
},
"linear_norm_rope": {
"mean_ms": 0.8369866923076922,
"n": 13,
"p50_ms": 0.8367649999999999,
"p95_ms": 0.8395509999999997,
"population_std_ms": 0.0014106170163667622
},
"moe": {
"mean_ms": 2.008448384615385,
"n": 13,
"p50_ms": 1.955683,
"p95_ms": 2.194793000000001,
"population_std_ms": 0.13403461779448436
},
"other": {
"mean_ms": 0.023700230769230772,
"n": 13,
"p50_ms": 0.023742999999999997,
"p95_ms": 0.024096,
"population_std_ms": 0.00023815901405643158
},
"output_head": {
"mean_ms": 0.045964538461538466,
"n": 13,
"p50_ms": 0.045856,
"p95_ms": 0.046624000000000006,
"population_std_ms": 0.0003695759764471495
},
"router": {
"mean_ms": 0.1853764615384615,
"n": 13,
"p50_ms": 0.18530699999999997,
"p95_ms": 0.18560199999999993,
"population_std_ms": 0.0001339481044082144
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_8(8)": 13,
"execute_context_1(4)_generation_7(7)": 1,
"execute_context_3(6144)_generation_1(1)": 1,
"execute_context_4(8188)_generation_4(4)": 1
},
"execute_wall": {
"mean_ms": 5.045370692307693,
"n": 13,
"p50_ms": 4.998862,
"p95_ms": 5.242511,
"population_std_ms": 0.13589867228614172
},
"gpu_kernel_busy": {
"mean_ms": 4.573969692307692,
"n": 13,
"p50_ms": 4.520643,
"p95_ms": 4.767782,
"population_std_ms": 0.13563036850452942
},
"non_kernel_gap": {
"mean_ms": 0.47140100000000024,
"n": 13,
"p50_ms": 0.4708439999999987,
"p95_ms": 0.48116299999999956,
"population_std_ms": 0.0040546694639067024
},
"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-r2-20260723-20260723T093027863838Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b8-r2/traces/profile/dp0_pp0_tp1_dcp0_ep1_rank1.1784799265964743771.pt.trace.json.gz"
},
{
"components": {
"attention": {
"mean_ms": 0.9081704615384611,
"n": 13,
"p50_ms": 0.9067839999999995,
"p95_ms": 0.9137029999999994,
"population_std_ms": 0.003844601502114216
},
"collective": {
"mean_ms": 0.5607229230769231,
"n": 13,
"p50_ms": 0.5606410000000001,
"p95_ms": 0.5753579999999999,
"population_std_ms": 0.005889349049330662
},
"linear_norm_rope": {
"mean_ms": 0.8375191538461533,
"n": 13,
"p50_ms": 0.8377699999999999,
"p95_ms": 0.8382449999999991,
"population_std_ms": 0.0007602619838080075
},
"moe": {
"mean_ms": 2.0034716923076927,
"n": 13,
"p50_ms": 1.9509769999999995,
"p95_ms": 2.1876420000000003,
"population_std_ms": 0.1321404819107208
},
"other": {
"mean_ms": 0.023784923076923075,
"n": 13,
"p50_ms": 0.023744,
"p95_ms": 0.024192,
"population_std_ms": 0.00026262885820062297
},
"output_head": {
"mean_ms": 0.04589046153846154,
"n": 13,
"p50_ms": 0.04592,
"p95_ms": 0.046464,
"population_std_ms": 0.0003319519463334356
},
"router": {
"mean_ms": 0.18966023076923072,
"n": 13,
"p50_ms": 0.18950599999999995,
"p95_ms": 0.19261299999999995,
"population_std_ms": 0.0014891042818184978
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_8(8)": 13,
"execute_context_1(4)_generation_7(7)": 1,
"execute_context_3(6144)_generation_1(1)": 1,
"execute_context_4(8188)_generation_4(4)": 1
},
"execute_wall": {
"mean_ms": 5.043654153846154,
"n": 13,
"p50_ms": 4.99831,
"p95_ms": 5.233926,
"population_std_ms": 0.1368864811675641
},
"gpu_kernel_busy": {
"mean_ms": 4.569219846153846,
"n": 13,
"p50_ms": 4.526768999999998,
"p95_ms": 4.755531999999999,
"population_std_ms": 0.13605665130991768
},
"non_kernel_gap": {
"mean_ms": 0.47443430769230827,
"n": 13,
"p50_ms": 0.47430400000000006,
"p95_ms": 0.48320900000000044,
"population_std_ms": 0.0038414357969708507
},
"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-r2-20260723-20260723T093027863838Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b8-r2/traces/profile/dp0_pp0_tp2_dcp0_ep2_rank2.1784799265970389602.pt.trace.json.gz"
},
{
"components": {
"attention": {
"mean_ms": 0.9173004615384611,
"n": 13,
"p50_ms": 0.915619999999999,
"p95_ms": 0.9253379999999995,
"population_std_ms": 0.0052849307922895015
},
"collective": {
"mean_ms": 0.5623942307692308,
"n": 13,
"p50_ms": 0.5634610000000001,
"p95_ms": 0.570651,
"population_std_ms": 0.006084772534195447
},
"linear_norm_rope": {
"mean_ms": 0.8376726923076918,
"n": 13,
"p50_ms": 0.8376949999999989,
"p95_ms": 0.8402979999999994,
"population_std_ms": 0.0016093297880994772
},
"moe": {
"mean_ms": 2.000759076923077,
"n": 13,
"p50_ms": 1.9501820000000014,
"p95_ms": 2.184468999999999,
"population_std_ms": 0.12953482671732042
},
"other": {
"mean_ms": 0.023644692307692308,
"n": 13,
"p50_ms": 0.023615999999999998,
"p95_ms": 0.023968,
"population_std_ms": 0.0002102991951465574
},
"output_head": {
"mean_ms": 0.04592738461538462,
"n": 13,
"p50_ms": 0.045824,
"p95_ms": 0.046688,
"population_std_ms": 0.0003889230769230783
},
"router": {
"mean_ms": 0.18559069230769226,
"n": 13,
"p50_ms": 0.18560099999999996,
"p95_ms": 0.18578999999999996,
"population_std_ms": 0.00010438640098240813
}
},
"execute_annotation_histogram": {
"execute_context_0(0)_generation_8(8)": 13,
"execute_context_1(4)_generation_7(7)": 1,
"execute_context_3(6144)_generation_1(1)": 1,
"execute_context_4(8188)_generation_4(4)": 1
},
"execute_wall": {
"mean_ms": 5.046865153846154,
"n": 13,
"p50_ms": 5.003904,
"p95_ms": 5.240352,
"population_std_ms": 0.1362175904832164
},
"gpu_kernel_busy": {
"mean_ms": 4.57328923076923,
"n": 13,
"p50_ms": 4.526548000000001,
"p95_ms": 4.767014999999998,
"population_std_ms": 0.13627994044452013
},
"non_kernel_gap": {
"mean_ms": 0.47357592307692375,
"n": 13,
"p50_ms": 0.474012000000001,
"p95_ms": 0.4803690000000005,
"population_std_ms": 0.0037547593482557514
},
"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-r2-20260723-20260723T093027863838Z/artifacts/runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b8-r2/traces/profile/dp0_pp0_tp3_dcp0_ep3_rank3.1784799265964152963.pt.trace.json.gz"
}
],
"schema": "frontier-decode-batch-trace.v1"
}