Cite
Notes
Only stored in your browser.
Attribution
SparAMX: Accelerating Compressed LLMs Token Generation on AMX-powered CPUs
arXiv 2025
from 1 papers
Ahmed F AbouElhamayed
Chi-Chih Chang
J. Pablo Muñoz
Jordan Dotzel
Mohamed S. Abdelfattah
Nilesh Jain
Vui Seng Chua
Yash Akhauri