ExpertFlow: Adaptive Expert Scheduling and Memory Coordination for Efficient MoE Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shen, Zixu, Chu, Kexin, Zhang, Yifan, Xiang, Dawei, Wu, Runxin, Zhang, Wei
Format:	Preprint
Published:	2025
Subjects:	Distributed, Parallel, and Cluster Computing Artificial Intelligence Performance
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.26730