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": 493.2576180040196,
|
|
"arrival": "burst:8",
|
|
"clean": {
|
|
"admitted": 2233,
|
|
"completed": 2233,
|
|
"completed_throughput_rps": 9.304166666666667,
|
|
"duration_s": 240.0,
|
|
"end_s": 300.0,
|
|
"failed": 0,
|
|
"input_tokens": 2858240,
|
|
"offered_rps": 9.304166666666667,
|
|
"output_tokens": 1143296,
|
|
"start_s": 60.0
|
|
},
|
|
"clean_segment_seconds": 80.0,
|
|
"drain_seconds": 14.923095890000695,
|
|
"elapsed_seconds": 508.1807138940203,
|
|
"failed_records": 0,
|
|
"load_point": "saturation",
|
|
"manifest_admitted": 3941,
|
|
"manifest_exhausted": false,
|
|
"manifest_rows": 32768,
|
|
"manifest_sha256": "0c4f835aae099265c3eb596d06c6c2fa7070dd280558eb289c602e8c3434dfe9",
|
|
"manifest_wrapped": false,
|
|
"max_in_flight": 256,
|
|
"num_clean_segments": 3,
|
|
"profiles": [
|
|
{
|
|
"start_call_s": 300.0054247789958,
|
|
"start_return_s": 323.45228312400286,
|
|
"start_status": 200,
|
|
"stop_call_s": 354.6066670610162,
|
|
"stop_return_s": 381.28106322701205,
|
|
"stop_status": 200,
|
|
"trace_file": "dp0_pp0_tp0_dcp0_ep0_rank0.1783835082061801278.pt.trace.json.gz",
|
|
"trace_ready_s": 354.6066622030048,
|
|
"trace_sha256": "53d36238e82e5d031d8ed7841094c56d715b7cd5009368b64e380bf89a0f0dec",
|
|
"window": 1
|
|
},
|
|
{
|
|
"start_call_s": 411.30330635100836,
|
|
"start_return_s": 411.4401313569979,
|
|
"start_status": 200,
|
|
"stop_call_s": 436.0742275560042,
|
|
"stop_return_s": 463.23921855099616,
|
|
"stop_status": 200,
|
|
"trace_file": "dp0_pp0_tp0_dcp0_ep0_rank0.1783835169024306574.pt.trace.json.gz",
|
|
"trace_ready_s": 436.0742245099973,
|
|
"trace_sha256": "e088bd800a4e43446effbbcd4fce7d9ba1defaceb378a6e0db04d64780e1d09a",
|
|
"window": 2
|
|
}
|
|
],
|
|
"rate_fraction": null,
|
|
"records": 3941,
|
|
"request_rate": "inf",
|
|
"schema": 1,
|
|
"segments": [
|
|
{
|
|
"admitted": 697,
|
|
"completed": 697,
|
|
"completed_throughput_rps": 8.7125,
|
|
"duration_s": 80.0,
|
|
"end_s": 140.0,
|
|
"failed": 0,
|
|
"input_tokens": 892160,
|
|
"name": "A",
|
|
"offered_rps": 8.7125,
|
|
"output_tokens": 356864,
|
|
"start_s": 60.0
|
|
},
|
|
{
|
|
"admitted": 768,
|
|
"completed": 768,
|
|
"completed_throughput_rps": 9.6,
|
|
"duration_s": 80.0,
|
|
"end_s": 220.0,
|
|
"failed": 0,
|
|
"input_tokens": 983040,
|
|
"name": "B",
|
|
"offered_rps": 9.6,
|
|
"output_tokens": 393216,
|
|
"start_s": 140.0
|
|
},
|
|
{
|
|
"admitted": 768,
|
|
"completed": 768,
|
|
"completed_throughput_rps": 9.6,
|
|
"duration_s": 80.0,
|
|
"end_s": 300.0,
|
|
"failed": 0,
|
|
"input_tokens": 983040,
|
|
"name": "C",
|
|
"offered_rps": 9.6,
|
|
"output_tokens": 393216,
|
|
"start_s": 220.0
|
|
}
|
|
],
|
|
"successful_records": 3941,
|
|
"t0_mono_ns": 166324009670273,
|
|
"t0_wall_ns": 1783834751136099481,
|
|
"warmup_seconds": 60.0
|
|
}
|