@misc{tyukin2024attention,
  title={Attention Is All You Need But You Don't Need All Of It For Inference of Large Language Models},
  author={Georgy Tyukin and Gbetondji J-S Dovonon and Jean Kaddour and Pasquale Minervini},
  year={2024},
  eprint={2407.15516},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2407.15516}
}