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>
75 lines
1.9 KiB
JSON
75 lines
1.9 KiB
JSON
{
|
|
"anchor": 0.033717411016,
|
|
"cell": "tp4_mns16",
|
|
"early_stop_reason": "",
|
|
"early_stopped": false,
|
|
"exact_output_count": 586,
|
|
"feasible": true,
|
|
"interval": {
|
|
"elapsed_s": 61.364052595,
|
|
"end_mono_ns": 201800328727441,
|
|
"end_wall_ns": 1783870227455155582,
|
|
"start_mono_ns": 201738964674846,
|
|
"start_wall_ns": 1783870166091102450
|
|
},
|
|
"invariants": {
|
|
"arrival_nondecreasing": true,
|
|
"exact_output_or_failed": true,
|
|
"outcomes_cover_selected": true,
|
|
"raw_lengths_present": true,
|
|
"selected_nonempty": true,
|
|
"warmup_16": true,
|
|
"warmup_exact_16": true,
|
|
"warmup_long": true
|
|
},
|
|
"kind": "anchor",
|
|
"mns": 16,
|
|
"observed_count": 586,
|
|
"pass_rate": 1.0,
|
|
"schema": 1,
|
|
"selection": {
|
|
"arrival_order_sha256": "fe44bf6b0efd6e6ab4d19676e34ace608827e419dbb5c19c8595992f0339c9b1",
|
|
"arrival_s": {
|
|
"distinct_n": 585,
|
|
"finite_n": 586,
|
|
"max": 59.90990000000002,
|
|
"min": 0.13000000000001818,
|
|
"missing_n": 0,
|
|
"n": 586
|
|
},
|
|
"count": 586,
|
|
"long_gt4096": 184,
|
|
"offered_req_s": 9.766666666666667,
|
|
"offered_req_s_per_gpu": 2.441666666666667,
|
|
"raw_input_tokens": {
|
|
"distinct_n": 534,
|
|
"finite_n": 586,
|
|
"max": 8157.0,
|
|
"min": 69.0,
|
|
"missing_n": 0,
|
|
"n": 586
|
|
},
|
|
"raw_length_order_sha256": "e2d040068b279e99073f6965d1136eb0ca6e8534c883f331b4cb85c5fc7a4650",
|
|
"request_id_order_sha256": "472a874ecc0e844b5b36a715bbc309b63e73074d39327cd734869f76721d71db"
|
|
},
|
|
"slo_pass_count": 586,
|
|
"study_sha256": "76e9d642ba9570917cfeeea848ed92f27904e87760eedabd48805b84e82eca26",
|
|
"tp": 4,
|
|
"tpot_ms": {
|
|
"distinct_n": 586,
|
|
"finite_n": 586,
|
|
"max": 14.420212055125647,
|
|
"min": 4.217363204660378,
|
|
"missing_n": 0,
|
|
"n": 586
|
|
},
|
|
"ttft_ms": {
|
|
"distinct_n": 586,
|
|
"finite_n": 586,
|
|
"max": 819.4046519929543,
|
|
"min": 36.395939998328686,
|
|
"missing_n": 0,
|
|
"n": 586
|
|
}
|
|
}
|