Speculative Decoding with a Speculative Vocabulary
arXiv:2602.13836v1 Announce Type: new Abstract: Speculative decoding has rapidly emerged as a leading approach for accelerating language model (LM) inference, as it offers substantial speedups …
Miles Williams, Young D. Kwon, Rui Li, Alexandros Kouris, Stylianos I. Venieris
3 views