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": 0.5,
|
|
"cell": "tp2_mns64",
|
|
"early_stop_reason": "slo_pass_rate_unrecoverable",
|
|
"early_stopped": true,
|
|
"exact_output_count": 142,
|
|
"feasible": false,
|
|
"interval": {
|
|
"elapsed_s": 32.625174607,
|
|
"end_mono_ns": 201195153573715,
|
|
"end_wall_ns": 1783869622280001349,
|
|
"start_mono_ns": 201162528399108,
|
|
"start_wall_ns": 1783869589654826388
|
|
},
|
|
"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": 276,
|
|
"pass_rate": 0.4601449275362319,
|
|
"schema": 1,
|
|
"selection": {
|
|
"arrival_order_sha256": "aeea4a8e54cc7de279804b8c353f748a480aedcbb21e249a90a60267daee8dff",
|
|
"arrival_s": {
|
|
"distinct_n": 276,
|
|
"finite_n": 276,
|
|
"max": 59.78950000000005,
|
|
"min": 0.008300000000008368,
|
|
"missing_n": 0,
|
|
"n": 276
|
|
},
|
|
"count": 276,
|
|
"long_gt4096": 99,
|
|
"offered_req_s": 4.6,
|
|
"offered_req_s_per_gpu": 2.3,
|
|
"raw_input_tokens": {
|
|
"distinct_n": 256,
|
|
"finite_n": 276,
|
|
"max": 8149.0,
|
|
"min": 71.0,
|
|
"missing_n": 0,
|
|
"n": 276
|
|
},
|
|
"raw_length_order_sha256": "983df528039301bd41a6684fecea75cdcf8822d214094d6d35def7fc7740c2ba",
|
|
"request_id_order_sha256": "3160017dbd8249f711eb115f1e72ddbb37eab3a3333a48762cc3104e94bd2f15"
|
|
},
|
|
"slo_pass_count": 127,
|
|
"study_sha256": "9474f0d0b53579f1db852ca68abfb0b96ba43ae4e17738118bf8e3209eb09ece",
|
|
"tp": 2,
|
|
"tpot_ms": {
|
|
"distinct_n": 142,
|
|
"finite_n": 142,
|
|
"max": 65.60344734654475,
|
|
"min": 4.993453378033802,
|
|
"missing_n": 134,
|
|
"n": 276
|
|
},
|
|
"ttft_ms": {
|
|
"distinct_n": 142,
|
|
"finite_n": 142,
|
|
"max": 1354.7493759833742,
|
|
"min": 39.566546998685226,
|
|
"missing_n": 134,
|
|
"n": 276
|
|
}
|
|
}
|