@misc{zhang2023heavy, title={H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models}, author={Zhenyu Zhang and Ying Sheng and Tianyi Zhou and Tianlong Chen and Lianmin Zheng and Ruisi Cai and Zhao Song and Yuandong Tian and Christopher RĂ© and Clark Barrett and Zhangyang Wang and Beidi Chen}, year={2023}, eprint={2306.14048}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2306.14048} }