CHAI: Clustered Head Attention for Efficient LLM Inference

Open Webpage

Saurabh Agarwal, Bilge Acun, Basil Hosmer, Mostafa Elhoushi, Yejin Lee, Shivaram Venkataraman, Dimitris Papailiopoulos, Carole-Jean Wu

Published: 01 Jan 2024, Last Modified: 15 May 2025ICML 2024EveryoneRevisionsBibTeXCC BY-SA 4.0