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": 0.4921875,
|
|
"cell": "tp2_mns8",
|
|
"early_stop_reason": "slo_pass_rate_unrecoverable",
|
|
"early_stopped": true,
|
|
"exact_output_count": 216,
|
|
"feasible": false,
|
|
"interval": {
|
|
"elapsed_s": 51.56724132,
|
|
"end_mono_ns": 201214250324754,
|
|
"end_wall_ns": 1783869641376751823,
|
|
"start_mono_ns": 201162683083434,
|
|
"start_wall_ns": 1783869589809510519
|
|
},
|
|
"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": 269,
|
|
"pass_rate": 0.6914498141263941,
|
|
"schema": 1,
|
|
"selection": {
|
|
"arrival_order_sha256": "ffbc7b8dd324c8e745654110a2412b03ddade891beb2bfe022ffde6502b0184b",
|
|
"arrival_s": {
|
|
"distinct_n": 269,
|
|
"finite_n": 269,
|
|
"max": 59.78950000000005,
|
|
"min": 0.008300000000008368,
|
|
"missing_n": 0,
|
|
"n": 269
|
|
},
|
|
"count": 269,
|
|
"long_gt4096": 95,
|
|
"offered_req_s": 4.483333333333333,
|
|
"offered_req_s_per_gpu": 2.2416666666666667,
|
|
"raw_input_tokens": {
|
|
"distinct_n": 250,
|
|
"finite_n": 269,
|
|
"max": 8149.0,
|
|
"min": 71.0,
|
|
"missing_n": 0,
|
|
"n": 269
|
|
},
|
|
"raw_length_order_sha256": "bc951350376a487d34d2def78fd32a2286e23bf8a7f481ff578009e12e3f1fb8",
|
|
"request_id_order_sha256": "cd227aee3be472a35e8c35af60a44a1411c4dc689cbd98746b3fb8a8d329b44c"
|
|
},
|
|
"slo_pass_count": 186,
|
|
"study_sha256": "9474f0d0b53579f1db852ca68abfb0b96ba43ae4e17738118bf8e3209eb09ece",
|
|
"tp": 2,
|
|
"tpot_ms": {
|
|
"distinct_n": 216,
|
|
"finite_n": 216,
|
|
"max": 22.936211125952685,
|
|
"min": 5.354799519524008,
|
|
"missing_n": 53,
|
|
"n": 269
|
|
},
|
|
"ttft_ms": {
|
|
"distinct_n": 216,
|
|
"finite_n": 216,
|
|
"max": 3692.623541021021,
|
|
"min": 40.143018995877355,
|
|
"missing_n": 53,
|
|
"n": 269
|
|
}
|
|
}
|