Workflow-Aware Expert Routing for Distributed LLM Serving Over the Edge-Cloud Continuum
Published in IEEE Transactions on Cognitive Communications and Networking, 2026
Recommended citation: Yan Gao, Shaoyuan Huang, Yonghui Ye, Jie Fu, Minglai Shao, Huaming Wu, Yansha Deng. (2026). "Workflow-Aware Expert Routing for Distributed LLM Serving Over the Edge-Cloud Continuum." IEEE Transactions on Cognitive Communications and Networking.
Download Paper