@article{kvserveserviceawarekvcachecompressionfor,
  title = {KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving},
  author = {Zedong Liu and Xinyang Ma and Dejun Luo and Hairui Zhao and Bing Lu and Wenjing Huang and Yida Gu and Xingchen Liu and Zheng Wei and Jinyang Liu and Dingwen Tao and Guangming Tan},
  year = {2026},
  eprint = {2605.13734},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.13734},
}