SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Ziyi, Jiang, Ziheng, Jiang, Chengquan, Yu, Menghan, Zheng, Size, Lin, Haibin, Hoffmann, Henry, Liu, Xin
Format:	Preprint
Published:	2025
Subjects:	Distributed, Parallel, and Cluster Computing Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2506.11309