@misc{yang2023inference,
  title={Inference with Reference: Lossless Acceleration of Large Language Models},
  author={Nan Yang and Tao Ge and Liang Wang and Binxing Jiao and Daxin Jiang and Linjun Yang and Rangan Majumder and Furu Wei},
  year={2023},
  eprint={2304.04487},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2304.04487}
}