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": 0.016591107009,
|
|
"cell": "tp4_mns8",
|
|
"early_stop_reason": "slo_pass_rate_unrecoverable",
|
|
"early_stopped": true,
|
|
"exact_output_count": 96,
|
|
"feasible": false,
|
|
"interval": {
|
|
"elapsed_s": 34.318039209,
|
|
"end_mono_ns": 201588003528635,
|
|
"end_wall_ns": 1783870015129955457,
|
|
"start_mono_ns": 201553685489426,
|
|
"start_wall_ns": 1783869980811916534
|
|
},
|
|
"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": 8,
|
|
"observed_count": 308,
|
|
"pass_rate": 0.07142857142857142,
|
|
"schema": 1,
|
|
"selection": {
|
|
"arrival_order_sha256": "860d2ac188790a401e93d3f99b9f37d6d69f0dfda1af94c37bc0067278444632",
|
|
"arrival_s": {
|
|
"distinct_n": 307,
|
|
"finite_n": 308,
|
|
"max": 59.75439999999999,
|
|
"min": 0.13000000000001818,
|
|
"missing_n": 0,
|
|
"n": 308
|
|
},
|
|
"count": 308,
|
|
"long_gt4096": 96,
|
|
"offered_req_s": 5.133333333333334,
|
|
"offered_req_s_per_gpu": 1.2833333333333334,
|
|
"raw_input_tokens": {
|
|
"distinct_n": 288,
|
|
"finite_n": 308,
|
|
"max": 8157.0,
|
|
"min": 69.0,
|
|
"missing_n": 0,
|
|
"n": 308
|
|
},
|
|
"raw_length_order_sha256": "c533dffff00fdea5f5492826549ca09fa62fe46ef98942928115816f92a38771",
|
|
"request_id_order_sha256": "2407501cda53bf9c761c448dc50ab4780b4a55958cc00ba1b19cd09de1cf73e1"
|
|
},
|
|
"slo_pass_count": 22,
|
|
"study_sha256": "76e9d642ba9570917cfeeea848ed92f27904e87760eedabd48805b84e82eca26",
|
|
"tp": 4,
|
|
"tpot_ms": {
|
|
"distinct_n": 96,
|
|
"finite_n": 96,
|
|
"max": 46.63372499200032,
|
|
"min": 4.1856984960787935,
|
|
"missing_n": 212,
|
|
"n": 308
|
|
},
|
|
"ttft_ms": {
|
|
"distinct_n": 96,
|
|
"finite_n": 96,
|
|
"max": 14333.491523982957,
|
|
"min": 39.389445999404415,
|
|
"missing_n": 212,
|
|
"n": 308
|
|
}
|
|
}
|