DiP-SD: Distributed Pipelined Speculative Decoding for Efficient LLM Inference at the Edge

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Yaodan, Zhou, Sheng, Niu, Zhisheng
Format:	Preprint
Published:	2026
Subjects:	Information Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.20919