@article{wkvquantquantizingweightandkeyvalue,
  title = {WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More},
  author = {Yuxuan Yue and Zhihang Yuan and Haojie Duanmu and Sifan Zhou and Jianlong Wu and Liqiang Nie},
  year = {2024},
  eprint = {2402.12065},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.12065v2},
}