@article{recursivespeculativedecodingaccelerating,
  title = {Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement},
  author = {Wonseok Jeon and Mukul Gagrani and Raghavv Goel and Junyoung Park and Mingu Lee and Christopher Lott},
  year = {2024},
  eprint = {2402.14160},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.14160v2},
}