Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Minsu, Hong, Seongmin, Ko, RyeoWook, Choi, Soongyu, Lee, Hunjong, Kim, Junsoo, Kim, Joo-Young, Park, Jongse
Format:	Preprint
Published:	2025
Subjects:	Hardware Architecture Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2503.18599