Dynamic Speculation Lookahead Accelerates Speculative Decoding of Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mamou, Jonathan, Pereg, Oren, Korat, Daniel, Berchansky, Moshe, Timor, Nadav, Wasserblat, Moshe, Schwartz, Roy
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2405.04304