NEO: Saving GPU Memory Crisis with CPU Offloading for Online LLM Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Xuanlin, Zhou, Yang, Cao, Shiyi, Stoica, Ion, Yu, Minlan
Format:	Preprint
Published:	2024
Subjects:	Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2411.01142