@article{losslessaccelerationoflargelanguagemodel,
  title = {Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel Decoding},
  author = {Jie Ou and Yueming Chen and Wenhong Tian},
  year = {2024},
  eprint = {2404.08698},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.08698v2},
}