SVDq: 1.25-bit and 410x Key Cache Compression for LLM Attention

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yankun, Hong, Xing, Li, Hui-Ling, Zhen, Xianzhi, Yu, Wulong, Liu, Mingxuan, Yuan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language 68T50
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.15304