Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cho, Sukmin, Choi, Sangjin, Hwang, Taeho, Seo, Jeongyeon, Jeong, Soyeong, Lee, Huije, Song, Hoyun, Park, Jong C., Kwon, Youngjin
Format:	Preprint
Published:	2025
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/2502.05609