@article{predictivepipelineddecodingacompute,
  title = {Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding},
  author = {Seongjun Yang and Gibbeum Lee and Jaewoong Cho and Dimitris Papailiopoulos and Kangwook Lee},
  year = {2023},
  eprint = {2307.05908},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2307.05908v2},
}