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>
2 lines
299 B
Plaintext
2 lines
299 B
Plaintext
CPU_ANALYSIS A-P3-7: accepted_runs=40, run_root=/home/admin/cpfs/wjh/opprof-phase3-dash0-20260712/runs/phase3, private_manifests=/home/admin/cpfs/wjh/opprof-phase3-private/manifests, bootstrap=100000 seed=20260714, output=runs/phase3/analysis/metrics-ap37.json, expected=10-30m CPU-only, GPU_cost=0
|