@article{mosaickvservinglongcontextllmwithdynamic, title = {MosaicKV: Serving Long-Context LLM with Dynamic Two-D KV Cache Compression}, author = {Sheng Qiang and Ruiwei Chen and Yinpeng Wu and Jinyu Gu and Zhichao Hua and Yubin Xia and Binyu Zang and Haibo Chen}, year = {2026}, eprint = {2607.00760}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.00760}, }