EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qian, Yulei, Li, Fengcun, Ji, Xiangyang, Zhao, Xiaoyu, Tan, Jianchao, Zhang, Kefeng, Cai, Xunliang
Format:	Preprint
Published:	2024
Subjects:	Computation and Language 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/2410.12247