Skip to main content
Vansh Verma
← Lab

spec-decode-acceptance

null resultPython · llama.cppInference & servingJuly 11, 2026

the question

Does draft-block acceptance in speculative decoding decay with depth?

what came out

No -- on a matched draft/target pair, acceptance is constant with depth (constant-alpha, empirically exact). The real structure is a boundary cold-start, and induced decay is an off-distribution-context effect, not self-conditioning drift. Exact TV oracle on Qwen2.5 0.5B/1.5B via llama.cpp.

method & receipts

  • Result: null result — an honest negative, reported as it came out.
  • Pre-registered — the prediction was written down and committed before the run.
  • Reproducible — one script re-runs the whole thing from scratch.

→ read the code and re-run it

github.com/v-code01/spec-decode-acceptance