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]

Authors

Mingjin Zhang

This author has not been identified. Look up 'Mingjin Zhang' in Google

Jiannong Cao 0001

This author has not been identified. Look up 'Jiannong Cao 0001' in Google

Tao Wu

This author has not been identified. Look up 'Tao Wu' in Google

Xiangchun Chen

This author has not been identified. Look up 'Xiangchun Chen' in Google

Ne Wang

This author has not been identified. Look up 'Ne Wang' in Google