VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yao, Dingyu, Yang, Chenxu, Tong, Zhengyang, Lin, Zheng, Liu, Wei, Luan, Jian, Wang, Weiping
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.06175