BanaServe: Unified KV Cache and Dynamic Module Migration for Balancing Disaggregated LLM Serving in AI Infrastructure

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	He, Yiyuan, Xu, Minxian, Wu, Jingfeng, Hu, Jianmin, Ma, Chong, Shen, Min, Chen, Le, Xu, Chengzhong, Qu, Lin, Ye, Kejiang
Format:	Preprint
Published:	2025
Subjects:	Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.13223