@article{nomadattentionefficientllminferenceon,
  title = {NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention},
  author = {Tianyi Zhang and Jonah Wonkyu Yi and Bowen Yao and Zhaozhuo Xu and Anshumali Shrivastava},
  year = {2024},
  eprint = {2403.01273},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.01273v1},
}