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": 417.66287675101194,
|
|
"arrival": "burst:8",
|
|
"clean": {
|
|
"admitted": 1226,
|
|
"completed": 1226,
|
|
"completed_throughput_rps": 5.108333333333333,
|
|
"duration_s": 240.0,
|
|
"end_s": 300.0,
|
|
"failed": 0,
|
|
"input_tokens": 1569280,
|
|
"offered_rps": 5.108333333333333,
|
|
"output_tokens": 627712,
|
|
"start_s": 60.0
|
|
},
|
|
"clean_segment_seconds": 80.0,
|
|
"drain_seconds": 26.098238860984566,
|
|
"elapsed_seconds": 443.7611156119965,
|
|
"failed_records": 0,
|
|
"load_point": "saturation",
|
|
"manifest_admitted": 2078,
|
|
"manifest_exhausted": false,
|
|
"manifest_rows": 32768,
|
|
"manifest_sha256": "74df66e21a705cd583493199a875e226e93d2da7cfede9bca81dfd9bcb8c9cc6",
|
|
"manifest_wrapped": false,
|
|
"max_in_flight": 256,
|
|
"num_clean_segments": 3,
|
|
"profiles": [
|
|
{
|
|
"start_call_s": 300.0039349270228,
|
|
"start_return_s": 300.9924320260179,
|
|
"start_status": 200,
|
|
"stop_call_s": 323.90002606701455,
|
|
"stop_return_s": 328.078528626007,
|
|
"stop_status": 200,
|
|
"trace_file": "dp0_pp0_tp0_dcp0_ep0_rank0.1783835058771060551.pt.trace.json.gz",
|
|
"trace_ready_s": 323.9000201699964,
|
|
"trace_sha256": "2d12038b03c6f9c28d1a488abd880ff2763e1f3c0ab502cfdd2507b649de2af7",
|
|
"window": 1
|
|
},
|
|
{
|
|
"start_call_s": 358.0940292410087,
|
|
"start_return_s": 358.8905565890018,
|
|
"start_status": 200,
|
|
"stop_call_s": 382.04741394601297,
|
|
"stop_return_s": 387.64796055300394,
|
|
"stop_status": 200,
|
|
"trace_file": "dp0_pp0_tp0_dcp0_ep0_rank0.1783835116964699401.pt.trace.json.gz",
|
|
"trace_ready_s": 382.04741024502437,
|
|
"trace_sha256": "2184d4f83ea22c0e5455dd3914922548ce8d3d5eba34f89562df69326e3832b5",
|
|
"window": 2
|
|
}
|
|
],
|
|
"rate_fraction": null,
|
|
"records": 2078,
|
|
"request_rate": "inf",
|
|
"schema": 1,
|
|
"segments": [
|
|
{
|
|
"admitted": 394,
|
|
"completed": 394,
|
|
"completed_throughput_rps": 4.925,
|
|
"duration_s": 80.0,
|
|
"end_s": 140.0,
|
|
"failed": 0,
|
|
"input_tokens": 504320,
|
|
"name": "A",
|
|
"offered_rps": 4.925,
|
|
"output_tokens": 201728,
|
|
"start_s": 60.0
|
|
},
|
|
{
|
|
"admitted": 397,
|
|
"completed": 397,
|
|
"completed_throughput_rps": 4.9625,
|
|
"duration_s": 80.0,
|
|
"end_s": 220.0,
|
|
"failed": 0,
|
|
"input_tokens": 508160,
|
|
"name": "B",
|
|
"offered_rps": 4.9625,
|
|
"output_tokens": 203264,
|
|
"start_s": 140.0
|
|
},
|
|
{
|
|
"admitted": 435,
|
|
"completed": 435,
|
|
"completed_throughput_rps": 5.4375,
|
|
"duration_s": 80.0,
|
|
"end_s": 300.0,
|
|
"failed": 0,
|
|
"input_tokens": 556800,
|
|
"name": "C",
|
|
"offered_rps": 5.4375,
|
|
"output_tokens": 222720,
|
|
"start_s": 220.0
|
|
}
|
|
],
|
|
"successful_records": 2078,
|
|
"t0_mono_ns": 166323999932716,
|
|
"t0_wall_ns": 1783834751126361482,
|
|
"warmup_seconds": 60.0
|
|
}
|