Faster LLM Inference using DBMS-Inspired Preemption and Cache Replacement Policies

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Kyoungmin, Li, Jiacheng, Hong, Kijae, Ailamaki, Anastasia
Format:	Preprint
Published:	2024
Subjects:	Performance Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2411.07447