@article{liu2024minicache, title={MiniCache: KV Cache Compression in Depth Dimension for Large Language Models}, author={Liu, Akide and Liu, Jing and Pan, Zizheng and He, Yefei and Haffari, Gholamreza and Zhuang, Bohan}, journal={arXiv preprint arXiv:2405.14366}, year={2024} }