@article{semipdtowardsefficientllmservingvia,
  title = {semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage},
  author = {Ke Hong and Lufang Chen and Zhong Wang and Xiuhong Li and Qiuli Mao and Jianping Ma and Chao Xiong and Guanyu Wu and Buhe Han and Guohao Dai and Yun Liang and Yu Wang},
  year = {2025},
  eprint = {2504.19867},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.19867v1},
}