SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Zihao, Cui, Bin, Gan, Shaoduo
Format:	Preprint
Published:	2024
Subjects:	Machine Learning 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/2404.04793