HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Haoran, Yu, Xianzhi, Zhao, Kang, Bao, Han, Zhan, Zongyuan, Hu, Ting, Liu, Wulong, Yin, Zekun, Li, Xin, Liu, Weiguo
Format:	Preprint
Published:	2025
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/2508.19373