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": 0.24609375,
|
|
"cell": "tp1_mns64",
|
|
"early_stop_reason": "",
|
|
"early_stopped": false,
|
|
"exact_output_count": 141,
|
|
"feasible": true,
|
|
"interval": {
|
|
"elapsed_s": 61.283849775,
|
|
"end_mono_ns": 199668751241940,
|
|
"end_wall_ns": 1783868095877669237,
|
|
"start_mono_ns": 199607467392165,
|
|
"start_wall_ns": 1783868034593819130
|
|
},
|
|
"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": 64,
|
|
"observed_count": 141,
|
|
"pass_rate": 1.0,
|
|
"schema": 1,
|
|
"selection": {
|
|
"arrival_order_sha256": "7c8f4ce3fc2db40d6329e8ead59378f564608ad6df09bc95854baef2dd0703d4",
|
|
"arrival_s": {
|
|
"distinct_n": 141,
|
|
"finite_n": 141,
|
|
"max": 59.78950000000005,
|
|
"min": 0.008300000000008368,
|
|
"missing_n": 0,
|
|
"n": 141
|
|
},
|
|
"count": 141,
|
|
"long_gt4096": 50,
|
|
"offered_req_s": 2.35,
|
|
"offered_req_s_per_gpu": 2.35,
|
|
"raw_input_tokens": {
|
|
"distinct_n": 133,
|
|
"finite_n": 141,
|
|
"max": 8149.0,
|
|
"min": 72.0,
|
|
"missing_n": 0,
|
|
"n": 141
|
|
},
|
|
"raw_length_order_sha256": "a30d27aea9630ed3623c73237867fbd3a6b7eec9bedec0f1c390610fd16ea5ba",
|
|
"request_id_order_sha256": "7e48c6bfc00eeadd6011111170c31123fb117c9fa75c18ccc8d8d505fd7fcff3"
|
|
},
|
|
"slo_pass_count": 141,
|
|
"study_sha256": "9474f0d0b53579f1db852ca68abfb0b96ba43ae4e17738118bf8e3209eb09ece",
|
|
"tp": 1,
|
|
"tpot_ms": {
|
|
"distinct_n": 141,
|
|
"finite_n": 141,
|
|
"max": 48.397922928960206,
|
|
"min": 4.49719877962177,
|
|
"missing_n": 0,
|
|
"n": 141
|
|
},
|
|
"ttft_ms": {
|
|
"distinct_n": 141,
|
|
"finite_n": 141,
|
|
"max": 1777.0718620158732,
|
|
"min": 49.70270599005744,
|
|
"missing_n": 0,
|
|
"n": 141
|
|
}
|
|
}
|