@article{acceleratinglargelanguagemodeldecoding,
  title = {Accelerating Large Language Model Decoding with Speculative Sampling},
  author = {Charlie Chen and Sebastian Borgeaud and Geoffrey Irving and Jean-Baptiste Lespiau and Laurent SIfre and John Jumper},
  year = {2023},
  eprint = {2302.01318},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2302.01318v1},
}