@article{rethinkingkeyvaluecachecompression, title = {Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving}, author = {Wei Gao and Xinyu Zhou and Peng Sun and Tianwei Zhang and Yonggang Wen}, year = {2025}, eprint = {2503.24000}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.24000v1}, }