@misc{zhang2024cache,
  title={KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization},
  author={Tianyi Zhang and Jonah Yi and Zhaozhuo Xu and Anshumali Shrivastava},
  year={2024},
  eprint={2405.03917},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2405.03917}
}