@article{adaptcachekvcachenativestoragehierarchyf, title = {AdaptCache: KV Cache Native Storage Hierarchy for Low-Delay and High-Quality Language Model Serving}, author = {Shaoting Feng and Hanchen Li and Kuntai Du and Zhuohan Gu and Yuhan Liu and Jiayi Yao and Siddhant Ray and Samuel Shen and Yihua Cheng and Ganesh Ananthanarayanan and Junchen Jiang}, year = {2025}, eprint = {2509.00105}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.00105}, }