@article{draftverifylosslesslargelanguagemodel,
  title = {Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding},
  author = {Jun Zhang and Jue Wang and Huan Li and Lidan Shou and Ke Chen and Gang Chen and Sharad Mehrotra},
  year = {2023},
  eprint = {2309.08168},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2309.08168v2},
}