Add OpProf campaign: protocols, results, patches, run evidence (P0-P6)

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>
This commit is contained in:
2026-07-13 11:06:10 +08:00
parent 607e88da3c
commit d5b276180d
412 changed files with 125056 additions and 0 deletions

View File

@@ -0,0 +1,103 @@
{
"admission_stop_s": 417.3262625900097,
"arrival": "steady",
"clean": {
"admitted": 559,
"completed": 559,
"completed_throughput_rps": 2.3291666666666666,
"duration_s": 240.0,
"end_s": 300.0,
"failed": 0,
"input_tokens": 3429894,
"offered_rps": 2.3291666666666666,
"output_tokens": 35776,
"start_s": 60.0
},
"clean_segment_seconds": 80.0,
"drain_seconds": 91.29178713698639,
"elapsed_seconds": 508.6180497269961,
"failed_records": 0,
"load_point": "saturation",
"manifest_admitted": 1094,
"manifest_exhausted": false,
"manifest_rows": 32768,
"manifest_sha256": "432cfbc26d36f105c179c83f3bb0f3b24b8b3f205788263b4171797f0a4d6fa1",
"manifest_wrapped": false,
"max_in_flight": 256,
"num_clean_segments": 3,
"profiles": [
{
"start_call_s": 300.0043962339987,
"start_return_s": 301.3819164079905,
"start_status": 200,
"stop_call_s": 321.8697677869932,
"stop_return_s": 326.31530767300865,
"stop_status": 200,
"trace_file": "dp0_pp0_tp0_dcp0_ep0_rank0.1783835059474707213.pt.trace.json.gz",
"trace_ready_s": 321.86976291501196,
"trace_sha256": "527ddb81b1d54a12a463508bc163d85a2c443d94c8a897959a39735e030b90a2",
"window": 1
},
{
"start_call_s": 356.32926020701416,
"start_return_s": 361.34978177401354,
"start_status": 200,
"stop_call_s": 381.577829301008,
"stop_return_s": 387.31277802900877,
"stop_status": 200,
"trace_file": "dp0_pp0_tp0_dcp0_ep0_rank0.1783835119198018909.pt.trace.json.gz",
"trace_ready_s": 381.57782580400817,
"trace_sha256": "0882d9705f1208580d5e693f94ba64d89ab12ef0aae2731a82d460a46a3e4cb1",
"window": 2
}
],
"rate_fraction": null,
"records": 1094,
"request_rate": "inf",
"schema": 1,
"segments": [
{
"admitted": 191,
"completed": 191,
"completed_throughput_rps": 2.3875,
"duration_s": 80.0,
"end_s": 140.0,
"failed": 0,
"input_tokens": 1154628,
"name": "A",
"offered_rps": 2.3875,
"output_tokens": 12224,
"start_s": 60.0
},
{
"admitted": 184,
"completed": 184,
"completed_throughput_rps": 2.3,
"duration_s": 80.0,
"end_s": 220.0,
"failed": 0,
"input_tokens": 1135217,
"name": "B",
"offered_rps": 2.3,
"output_tokens": 11776,
"start_s": 140.0
},
{
"admitted": 184,
"completed": 184,
"completed_throughput_rps": 2.3,
"duration_s": 80.0,
"end_s": 300.0,
"failed": 0,
"input_tokens": 1140049,
"name": "C",
"offered_rps": 2.3,
"output_tokens": 11776,
"start_s": 220.0
}
],
"successful_records": 1094,
"t0_mono_ns": 166323993366724,
"t0_wall_ns": 1783834751119796663,
"warmup_seconds": 60.0
}