Toggle navigation
OpenReview
.net
Login
×
Go to
DBLP
homepage
SparQ Attention: Bandwidth-Efficient LLM Inference
Luka Ribar
,
Ivan Chelombiev
,
Luke Hudlass-Galley
,
Charlie Blake
,
Carlo Luschi
,
Douglas Orr
Published: 01 Jan 2024, Last Modified: 15 May 2025
ICML 2024
Everyone
Revisions
BibTeX
CC BY-SA 4.0
Loading