Search Results for author: Luke Hudlass-Galley

Found 1 papers, 1 papers with code

SparQ Attention: Bandwidth-Efficient LLM Inference

1 code implementation • 8 Dec 2023 • Luka Ribar, Ivan Chelombiev, Luke Hudlass-Galley, Charlie Blake, Carlo Luschi, Douglas Orr

The computational difficulties of large language model (LLM) inference remain a significant obstacle to their widespread deployment.

Language Modelling Large Language Model

13

Paper
Code

Cannot find the paper you are looking for? You can Submit a new open access paper.