RelayAttention for Efficient Large Language Model Serving with Long System Prompts

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhu, Lei, Wang, Xinjiang, Zhang, Wayne, Lau, Rynson W. H.
Format:	Preprint
Published:	2024
Subjects:	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/2402.14808