InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pan, Xiurui, Li, Endian, Li, Qiao, Liang, Shengwen, Shan, Yizhou, Zhou, Ke, Luo, Yingwei, Wang, Xiaolin, Zhang, Jie
Format:	Preprint
Published:	2024
Subjects:	Hardware Architecture Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2409.04992