@article{flowkvadisaggregatedinferenceframework, title = {FlowKV: A Disaggregated Inference Framework with Low-Latency KV Cache Transfer and Load-Aware Scheduling}, author = {Weiqing Li and Guochao Jiang and Xiangyong Ding and Zhangcheng Tao and Chuzhan Hao and Chenfeng Xu and Yuewei Zhang and Hao Wang}, year = {2025}, eprint = {2504.03775}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.03775v1}, }