PROBE: Co-Balancing Computation and Communication in MoE Inference via Real-Time Predictive Prefetching

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhu, Qianchao, Ye, Xucheng, Liu, Yuliang, Ouyang, Haodong, Song, Chengru
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/2602.00509