Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline Parallelism

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Yijiong, Wang, Huazheng, Yuan, Shuai, Ren, Ruilong, Pei, Ji
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!