@misc{alizadeh2023flash,
  title={LLM in a flash: Efficient Large Language Model Inference with Limited Memory},
  author={Keivan Alizadeh and Iman Mirzadeh and Dmitry Belenko and Karen Khatamifard and Minsik Cho and Carlo C Del Mundo and Mohammad Rastegari and Mehrdad Farajtabar},
  year={2023},
  eprint={2312.11514},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2312.11514}
}