Fast MoE Inference via Predictive Prefetching and Expert Replication

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jyothish, Ankit, Jannesari, Ali, Sarkar, Aishwarya, Zuber, Joseph
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2605.11537