FASER: Fine-Grained Phase Management for Speculative Decoding in Dynamic LLM Serving

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Wenyan, Lu, Chengzhi, Lin, Yanying, Ustiugov, Dmitrii
Format:	Preprint
Published:	2026
Subjects:	Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.20503