@article{towardsefficientkeyvaluecachemanagement, title = {Towards Efficient Key-Value Cache Management for Prefix Prefilling in LLM Inference}, author = {Yue Zhu and Hao Yu and Chen Wang and Zhuoran Liu and Eun Kyung Lee}, year = {2025}, eprint = {2505.21919}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.21919v1}, }