MergeMoE: Efficient Compression of MoE Models via Expert Output Merging

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Miao, Ruijie, Yao, Yilun, Wang, Zihan, Wang, Zhiming, Yi, Bairen, Liu, LingJun, Zhao, Yikai, Yang, Tong
Format:	Preprint
Published:	2025
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/2510.14436