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>
104 lines
2.8 KiB
JSON
104 lines
2.8 KiB
JSON
{
|
|
"admission_stop_s": 420.6437278209778,
|
|
"arrival": "steady",
|
|
"clean": {
|
|
"admitted": 178,
|
|
"completed": 178,
|
|
"completed_throughput_rps": 0.7416666666666667,
|
|
"duration_s": 240.0,
|
|
"end_s": 300.0,
|
|
"failed": 0,
|
|
"input_tokens": 1755158,
|
|
"offered_rps": 0.7416666666666667,
|
|
"output_tokens": 40658,
|
|
"start_s": 60.0
|
|
},
|
|
"clean_segment_seconds": 80.0,
|
|
"drain_seconds": 288.6191079240234,
|
|
"elapsed_seconds": 709.2628357450012,
|
|
"failed_records": 0,
|
|
"load_point": "saturation",
|
|
"manifest_admitted": 558,
|
|
"manifest_exhausted": false,
|
|
"manifest_rows": 4011,
|
|
"manifest_sha256": "f51b7a1cc657d62b9ea81823c754408732326b06e03439452433cd8ed481bf33",
|
|
"manifest_wrapped": false,
|
|
"max_in_flight": 256,
|
|
"num_clean_segments": 3,
|
|
"profiles": [
|
|
{
|
|
"start_call_s": 300.0035294489935,
|
|
"start_return_s": 310.3520467719936,
|
|
"start_status": 200,
|
|
"stop_call_s": 325.0655262139917,
|
|
"stop_return_s": 338.54296391498065,
|
|
"stop_status": 200,
|
|
"trace_file": "dp0_pp0_tp0_dcp0_ep0_rank0.1783835066783986388.pt.trace.json.gz",
|
|
"trace_ready_s": 325.0655210709956,
|
|
"trace_sha256": "d457af416fa91f44e617c7259167fca467bea8466a3e4c4b916f811fb5899c73",
|
|
"window": 1
|
|
},
|
|
{
|
|
"start_call_s": 368.55468072599615,
|
|
"start_return_s": 372.31818850699347,
|
|
"start_status": 200,
|
|
"stop_call_s": 386.0271748309897,
|
|
"stop_return_s": 390.6334540609969,
|
|
"stop_status": 200,
|
|
"trace_file": "dp0_pp0_tp0_dcp0_ep0_rank0.1783835128341345321.pt.trace.json.gz",
|
|
"trace_ready_s": 386.02717122397735,
|
|
"trace_sha256": "41e8b34a0464cfd92d16b21c6242113b23594081697f5d1e88cdc3647542a96a",
|
|
"window": 2
|
|
}
|
|
],
|
|
"rate_fraction": null,
|
|
"records": 558,
|
|
"request_rate": "inf",
|
|
"schema": 1,
|
|
"segments": [
|
|
{
|
|
"admitted": 48,
|
|
"completed": 48,
|
|
"completed_throughput_rps": 0.6,
|
|
"duration_s": 80.0,
|
|
"end_s": 140.0,
|
|
"failed": 0,
|
|
"input_tokens": 548329,
|
|
"name": "A",
|
|
"offered_rps": 0.6,
|
|
"output_tokens": 11027,
|
|
"start_s": 60.0
|
|
},
|
|
{
|
|
"admitted": 70,
|
|
"completed": 70,
|
|
"completed_throughput_rps": 0.875,
|
|
"duration_s": 80.0,
|
|
"end_s": 220.0,
|
|
"failed": 0,
|
|
"input_tokens": 574251,
|
|
"name": "B",
|
|
"offered_rps": 0.875,
|
|
"output_tokens": 16298,
|
|
"start_s": 140.0
|
|
},
|
|
{
|
|
"admitted": 60,
|
|
"completed": 60,
|
|
"completed_throughput_rps": 0.75,
|
|
"duration_s": 80.0,
|
|
"end_s": 300.0,
|
|
"failed": 0,
|
|
"input_tokens": 632578,
|
|
"name": "C",
|
|
"offered_rps": 0.75,
|
|
"output_tokens": 13333,
|
|
"start_s": 220.0
|
|
}
|
|
],
|
|
"successful_records": 558,
|
|
"t0_mono_ns": 166325149689000,
|
|
"t0_wall_ns": 1783834752276118250,
|
|
"warmup_seconds": 60.0
|
|
}
|