SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Xiangchen, Spatharakis, Dimitrios, Ghafouri, Saeid, Fan, Jiakun, Vandierendonck, Hans, John, Deepu, Ji, Bo, Nikolopoulos, Dimitrios
Format:	Preprint
Published:	2025
Subjects:	Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning Networking and Internet Architecture 68T07, 68M14 I.2.6; C.2.4; C.1.4
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2506.09397