CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Luning, Li, Shiyao, Ning, Xuefei, Yuan, Zhihang, Yan, Shengen, Dai, Guohao, Wang, Yu
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence 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/2409.10593