FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jo, Dongwon, Song, Jiwon, Kim, Yulhwa, Kim, Jae-Joon
Format:	Preprint
Published:	2025
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/2502.01068