ATP: Enabling Fast LLM Serving via Attention on Top Principal Keys

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Niu, Yue, Prakash, Saurav, Avestimehr, Salman
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2403.02352