@article{skipdecodeautoregressiveskipdecodingwith,
  title = {SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference},
  author = {Luciano del Corro and Allie Del Giorno and Sahaj Agarwal and Bin Yu and Ahmed Awadallah and Subhabrata Mukherjee},
  year = {2023},
  eprint = {2307.02628},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2307.02628v1},
}