@article{promptcachemodularattentionreuseforlow,
  title = {Prompt Cache: Modular Attention Reuse for Low-Latency Inference},
  author = {In Gim and Guojun Chen and Seung-seob Lee and Nikhil Sarda and Anurag Khandelwal and Lin Zhong},
  year = {2023},
  eprint = {2311.04934},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.04934v2},
}