@article{swiftontheflyselfspeculativedecoding,
  title = {SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration},
  author = {Heming Xia and Yongqi Li and Jun Zhang and Cunxiao Du and Wenjie Li},
  year = {2024},
  eprint = {2410.06916},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.06916v1},
}