COMET: Towards Partical W4A4KV4 LLMs Serving

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Lian, Ren, Haimeng, Cheng, Long, Xu, Zhaohui, Pan, Yudong, Wang, Mengdi, Li, Xiaowei, Han, Yinhe, Wang, Ying
Format:	Preprint
Published:	2024
Subjects:	Hardware Architecture Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2410.12168