ViBE: Co-Optimizing Workload Skew and Hardware Variability for MoE Serving

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Go, Seokjin, Scrbak, Marko, Wu, Ephrem, Manne, Srilatha, Mahajan, Divya
Format:	Preprint
Published:	2026
Subjects:	Distributed, Parallel, and Cluster Computing Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2606.00735