@article{unlockingefficiencyinlargelanguagemodel,
  title = {Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding},
  author = {Heming Xia and Zhe Yang and Qingxiu Dong and Peiyi Wang and Yongqi Li and Tao Ge and Tianyu Liu and Wenjie Li and Zhifang Sui},
  year = {2024},
  eprint = {2401.07851},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.07851v3},
}