@misc{xiao2023efficient,
  title={Efficient Streaming Language Models with Attention Sinks},
  author={Guangxuan Xiao and Yuandong Tian and Beidi Chen and Song Han and Mike Lewis},
  year={2023},
  eprint={2309.17453},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2309.17453}
}