Preprint
Aug 2026
Oilbird: Training-Free Speculative Decoding with Keys the Verifier Already Computes
A second, semantic draft source is proposed: the same pool, re-keyed by the hidden state the verifier has already computed at each committed token, together with a merge that lets it ride inside an existing lexical drafter's tree.
Tao Jin, P. Nguyen, Zhenzhu Yan et al.
· 0 citations