paperIEEE Xplore·1 Nov 2026·Dong Dong, Chengzhang Wu, Zheng Chen, Longchuan Yan, Jianing Niu
EcoxPU: Autonomous Multi-Agent Orchestration for Energy-Efficient Disaggregated LLM Inference on Heterogeneous xPUs
EcoxPU orchestrates disaggregated LLM inference across heterogeneous accelerators with agents to cut energy use.
Extract
IEEE Transactions on Parallel and Distributed Systems