@article{minicachekvcachecompressionindepth, title = {MiniCache: KV Cache Compression in Depth Dimension for Large Language Models}, author = {Akide Liu and Jing Liu and Zizheng Pan and Yefei He and Gholamreza Haffari and Bohan Zhuang}, year = {2024}, eprint = {2405.14366}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.14366v2}, }