@article{sparamxacceleratingcompressedllmstoken, title = {SparAMX: Accelerating Compressed LLMs Token Generation on AMX-powered CPUs}, author = {Ahmed F. AbouElhamayed and Jordan Dotzel and Yash Akhauri and Chi-Chih Chang and Sameh Gobriel and J. Pablo Muñoz and Vui Seng Chua and Nilesh Jain and Mohamed S. Abdelfattah}, year = {2025}, eprint = {2502.12444}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.12444v1}, }