Inference Spec Decode Tune

Run a bounded comparison of speculative decoding draft training settings. Use measured serving acceptance and latency as the decision metrics, with training accuracy only as a triage signal. Use when one draft recipe already trains correctly and the operator can provide reproducible train and evaluation commands for each candidate.

cfregly Updated 4 repo stars

File contents

cfregly/claude-perf-tune commit 8e035c8d14

Frequently asked questions

npx get-skill add cfregly/inference-spec-decode-tune-2