Gahow Wang
d5b276180d
Workload-conditioned operator profiling on patched vLLM 0.24.0 + Qwen3-30B-A3B/H20. H1b PASS (irregular patterns carry +23-45pp R64 raggedness, 8-45% token-efficiency loss vs rectangular controls); mechanism decomposition kills the padding narrative and finds the arrival-uniformization artifact (-12.9%); cross-version churn surface shows TP2/MNS64 -29.4% across vLLM 0.20->0.24 while the argmax held. Raw Layer-1 JSONL streams (507 MB) stay on disk, git-ignored; footer sidecars and metrics are tracked. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
92 lines
1.4 KiB
JSON
92 lines
1.4 KiB
JSON
{
|
|
"arm": "ON",
|
|
"bucket_tokens": 227714,
|
|
"capture_sizes": [
|
|
1,
|
|
2,
|
|
3,
|
|
4,
|
|
5,
|
|
6,
|
|
7,
|
|
8,
|
|
9,
|
|
16,
|
|
24,
|
|
32,
|
|
40,
|
|
48,
|
|
56,
|
|
64,
|
|
72,
|
|
80,
|
|
88,
|
|
96,
|
|
104,
|
|
112,
|
|
120,
|
|
128,
|
|
136,
|
|
144,
|
|
152,
|
|
160,
|
|
168,
|
|
176,
|
|
184,
|
|
192,
|
|
200,
|
|
208,
|
|
216,
|
|
224,
|
|
232,
|
|
240,
|
|
248,
|
|
256,
|
|
272,
|
|
288,
|
|
304,
|
|
320,
|
|
336,
|
|
352,
|
|
368,
|
|
384,
|
|
400,
|
|
416,
|
|
432,
|
|
448,
|
|
464,
|
|
480,
|
|
496,
|
|
512
|
|
],
|
|
"clean_completed": 1190,
|
|
"clean_completed_throughput_rps": 4.958333333333333,
|
|
"clean_failed": 0,
|
|
"clean_offered_rps": 4.920833333333333,
|
|
"drain_seconds": 0.7876331160077825,
|
|
"e2e_latency_mean_s": 1.612280680370388,
|
|
"e2e_latency_p95_s": 3.9930475192406423,
|
|
"gpu_hours": 0.15887338949574364,
|
|
"graph_hit_steps": 14253,
|
|
"graph_miss_rate": 0.0389724226282786,
|
|
"layer1_invariants": {
|
|
"cudagraph_identity": true,
|
|
"footer_balanced": true,
|
|
"footer_written_matches": true,
|
|
"schema_1": true,
|
|
"sidecar_agrees": true,
|
|
"sidecar_final": true,
|
|
"steps_unique_contiguous": true,
|
|
"token_composition": true,
|
|
"zero_drops": true
|
|
},
|
|
"layer1_records": 17579,
|
|
"model_step_duration_ms": 478655.543996,
|
|
"model_steps": 14831,
|
|
"padding_fraction": 0.035658764941988635,
|
|
"padding_tokens": 8120,
|
|
"schema": 1,
|
|
"token_efficiency_per_ms": 4.562222306607711,
|
|
"useful_tokens": 2183733
|
|
}
|