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_mns16",
|
|
"early_stop_reason": "",
|
|
"early_stopped": false,
|
|
"exact_output_count": 16,
|
|
"feasible": true,
|
|
"interval": {
|
|
"elapsed_s": 8.031388113,
|
|
"end_mono_ns": 199530259142500,
|
|
"end_wall_ns": 1783867957385569525,
|
|
"start_mono_ns": 199522227754387,
|
|
"start_wall_ns": 1783867949354181463
|
|
},
|
|
"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": "warmup",
|
|
"mns": 16,
|
|
"observed_count": 16,
|
|
"pass_rate": 1.0,
|
|
"schema": 1,
|
|
"selection": {
|
|
"arrival_order_sha256": "1bfb7b673b63b8aaea00c075792180307e1a32e354711a8d3c4978f9a013bc02",
|
|
"arrival_s": {
|
|
"distinct_n": 16,
|
|
"finite_n": 16,
|
|
"max": 6.901699999999983,
|
|
"min": 0.0,
|
|
"missing_n": 0,
|
|
"n": 16
|
|
},
|
|
"count": 16,
|
|
"long_gt4096": 8,
|
|
"offered_req_s": 0.26666666666666666,
|
|
"offered_req_s_per_gpu": 0.26666666666666666,
|
|
"raw_input_tokens": {
|
|
"distinct_n": 16,
|
|
"finite_n": 16,
|
|
"max": 7270.0,
|
|
"min": 72.0,
|
|
"missing_n": 0,
|
|
"n": 16
|
|
},
|
|
"raw_length_order_sha256": "e858719eb07cdeb674aa17d9299d05dec852db11c263bc9391c53cd0f177db1c",
|
|
"request_id_order_sha256": "0fa4b7f4dc274280eb173a0ee0974643ab283b887418ce8f10e958e7e8d90161"
|
|
},
|
|
"slo_pass_count": 16,
|
|
"study_sha256": "9474f0d0b53579f1db852ca68abfb0b96ba43ae4e17738118bf8e3209eb09ece",
|
|
"tp": 1,
|
|
"tpot_ms": {
|
|
"distinct_n": 16,
|
|
"finite_n": 16,
|
|
"max": 28.370322086701652,
|
|
"min": 4.984751267873821,
|
|
"missing_n": 0,
|
|
"n": 16
|
|
},
|
|
"ttft_ms": {
|
|
"distinct_n": 16,
|
|
"finite_n": 16,
|
|
"max": 696.6323160158936,
|
|
"min": 74.85444800113328,
|
|
"missing_n": 0,
|
|
"n": 16
|
|
}
|
|
}
|