Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fang, Yunhua, Xie, Rui, Haq, Asad Ul, Ma, Linsen, Maghraoui, Kaoutar El, Wang, Naigang, Wang, Meng, Liu, Liu, Zhang, Tong
Format:	Preprint
Published:	2025
Subjects:	Hardware Architecture Artificial Intelligence Performance
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2508.13231