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>
17 lines
581 B
JSON
17 lines
581 B
JSON
{
|
|
"at": 1783834288.13871,
|
|
"finding": "Explicit MBT=2048 is logged in non-default args; scheduler.py emits the separate Chunked-prefill line only for default MBT.",
|
|
"gpu_rerun": false,
|
|
"kind": "validator-only",
|
|
"new_controller_sha256": "c2d3232fb99c66cea55e30e6cb1aa6a84d3a816434ed8155a309f41df2837f73",
|
|
"old_controller_sha256": "74859614a8da3341bf827bb75b667db7d219f059d1d29c1182b9a77c2ee59e92",
|
|
"protocol_or_workload_changed": false,
|
|
"revalidated_runs": [
|
|
"P06-C00-burnin",
|
|
"P06-C10-burnin",
|
|
"P06-C01-burnin",
|
|
"P06-C11-burnin"
|
|
],
|
|
"schema": 1
|
|
}
|