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": 363.15318555399426,
|
|
"arrival": "steady",
|
|
"clean": {
|
|
"admitted": 113,
|
|
"completed": 111,
|
|
"completed_throughput_rps": 0.4625,
|
|
"duration_s": 240.0,
|
|
"end_s": 300.0,
|
|
"failed": 0,
|
|
"input_tokens": 968714,
|
|
"offered_rps": 0.4708333333333333,
|
|
"output_tokens": 25409,
|
|
"start_s": 60.0
|
|
},
|
|
"clean_segment_seconds": 80.0,
|
|
"drain_seconds": 1.3658369119802956,
|
|
"elapsed_seconds": 364.51902246597456,
|
|
"failed_records": 0,
|
|
"load_point": "moderate",
|
|
"manifest_admitted": 172,
|
|
"manifest_exhausted": false,
|
|
"manifest_rows": 4011,
|
|
"manifest_sha256": "f51b7a1cc657d62b9ea81823c754408732326b06e03439452433cd8ed481bf33",
|
|
"manifest_wrapped": false,
|
|
"max_in_flight": 7,
|
|
"num_clean_segments": 3,
|
|
"profiles": [
|
|
{
|
|
"start_call_s": 300.00394913199125,
|
|
"start_return_s": 300.03973603399936,
|
|
"start_status": 200,
|
|
"stop_call_s": 300.89519165997626,
|
|
"stop_return_s": 301.6286224719952,
|
|
"stop_status": 200,
|
|
"trace_file": "dp0_pp0_tp0_dcp0_ep0_rank0.1783849466906401944.pt.trace.json.gz",
|
|
"trace_ready_s": 300.8951868820004,
|
|
"trace_sha256": "a15670f86d843d40e7c4b6f354dd0193ea1259824a96440392d923f5270ba095",
|
|
"window": 1
|
|
},
|
|
{
|
|
"start_call_s": 331.62960390897933,
|
|
"start_return_s": 331.63382844498847,
|
|
"start_status": 200,
|
|
"stop_call_s": 332.4971265429922,
|
|
"stop_return_s": 333.15040952397976,
|
|
"stop_status": 200,
|
|
"trace_file": "dp0_pp0_tp0_dcp0_ep0_rank0.1783849498465727706.pt.trace.json.gz",
|
|
"trace_ready_s": 332.4971234249824,
|
|
"trace_sha256": "0f5962e193e09a9b2f1df6cea23f92419dcf2b322ee4ef2135a4fc3e1fe0617c",
|
|
"window": 2
|
|
}
|
|
],
|
|
"rate_fraction": 0.6,
|
|
"records": 172,
|
|
"request_rate": 0.4725,
|
|
"schema": 1,
|
|
"segments": [
|
|
{
|
|
"admitted": 38,
|
|
"completed": 37,
|
|
"completed_throughput_rps": 0.4625,
|
|
"duration_s": 80.0,
|
|
"end_s": 140.0,
|
|
"failed": 0,
|
|
"input_tokens": 404192,
|
|
"name": "A",
|
|
"offered_rps": 0.475,
|
|
"output_tokens": 8525,
|
|
"start_s": 60.0
|
|
},
|
|
{
|
|
"admitted": 37,
|
|
"completed": 38,
|
|
"completed_throughput_rps": 0.475,
|
|
"duration_s": 80.0,
|
|
"end_s": 220.0,
|
|
"failed": 0,
|
|
"input_tokens": 327301,
|
|
"name": "B",
|
|
"offered_rps": 0.4625,
|
|
"output_tokens": 8617,
|
|
"start_s": 140.0
|
|
},
|
|
{
|
|
"admitted": 38,
|
|
"completed": 36,
|
|
"completed_throughput_rps": 0.45,
|
|
"duration_s": 80.0,
|
|
"end_s": 300.0,
|
|
"failed": 0,
|
|
"input_tokens": 237221,
|
|
"name": "C",
|
|
"offered_rps": 0.475,
|
|
"output_tokens": 8267,
|
|
"start_s": 220.0
|
|
}
|
|
],
|
|
"successful_records": 172,
|
|
"t0_mono_ns": 180739547167834,
|
|
"t0_wall_ns": 1783849166673595809,
|
|
"warmup_seconds": 60.0
|
|
}
|