Efficient KV Cache Migration for Geo-Distributed LLM Inference in Collaborative Edge Computing

Mingjin Zhang, Jiannong Cao 0001, Tao Wu, Xiangchun Chen, Ne Wang. Efficient KV Cache Migration for Geo-Distributed LLM Inference in Collaborative Edge Computing. In 46th IEEE International Conference on Distributed Computing Systems, ICDCS 2026, Seoul, Republic of Korea, June 22-25, 2026. pages 272-282, IEEE, 2026. [doi]

@inproceedings{ZhangCWCW26,
  title = {Efficient KV Cache Migration for Geo-Distributed LLM Inference in Collaborative Edge Computing},
  author = {Mingjin Zhang and Jiannong Cao 0001 and Tao Wu and Xiangchun Chen and Ne Wang},
  year = {2026},
  doi = {10.1109/2575-8411.2026.00033},
  url = {https://doi.org/10.1109/2575-8411.2026.00033},
  researchr = {https://researchr.org/publication/ZhangCWCW26},
  cites = {0},
  citedby = {0},
  pages = {272-282},
  booktitle = {46th IEEE International Conference on Distributed Computing Systems, ICDCS 2026, Seoul, Republic of Korea, June 22-25, 2026},
  publisher = {IEEE},
  isbn = {979-8-3195-2979-4},
}