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": 0.033182214016,
|
|
"cell": "tp4_mns16",
|
|
"early_stop_reason": "slo_pass_rate_unrecoverable",
|
|
"early_stopped": true,
|
|
"exact_output_count": 413,
|
|
"feasible": false,
|
|
"interval": {
|
|
"elapsed_s": 49.259978895,
|
|
"end_mono_ns": 201650764016357,
|
|
"end_wall_ns": 1783870077890443949,
|
|
"start_mono_ns": 201601504037462,
|
|
"start_wall_ns": 1783870028630464875
|
|
},
|
|
"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": 16,
|
|
"observed_count": 575,
|
|
"pass_rate": 0.6086956521739131,
|
|
"schema": 1,
|
|
"selection": {
|
|
"arrival_order_sha256": "86ee457cd91595c76454d54ebc69890836ef603ceb96deaf9c7cf05e91de9407",
|
|
"arrival_s": {
|
|
"distinct_n": 574,
|
|
"finite_n": 575,
|
|
"max": 59.90990000000002,
|
|
"min": 0.13000000000001818,
|
|
"missing_n": 0,
|
|
"n": 575
|
|
},
|
|
"count": 575,
|
|
"long_gt4096": 178,
|
|
"offered_req_s": 9.583333333333334,
|
|
"offered_req_s_per_gpu": 2.3958333333333335,
|
|
"raw_input_tokens": {
|
|
"distinct_n": 524,
|
|
"finite_n": 575,
|
|
"max": 8157.0,
|
|
"min": 69.0,
|
|
"missing_n": 0,
|
|
"n": 575
|
|
},
|
|
"raw_length_order_sha256": "8354300b1680841ab43ef8164307d7c1f28bc877994b8d1e7584aff030677560",
|
|
"request_id_order_sha256": "e6b624a0212807df3733c54b4a2160fba24f19ca4776b14f34918d83428bba7f"
|
|
},
|
|
"slo_pass_count": 350,
|
|
"study_sha256": "76e9d642ba9570917cfeeea848ed92f27904e87760eedabd48805b84e82eca26",
|
|
"tp": 4,
|
|
"tpot_ms": {
|
|
"distinct_n": 413,
|
|
"finite_n": 413,
|
|
"max": 16.932683684963983,
|
|
"min": 4.637226771506459,
|
|
"missing_n": 162,
|
|
"n": 575
|
|
},
|
|
"ttft_ms": {
|
|
"distinct_n": 413,
|
|
"finite_n": 413,
|
|
"max": 4166.508020018227,
|
|
"min": 38.04149298230186,
|
|
"missing_n": 162,
|
|
"n": 575
|
|
}
|
|
}
|