Adaptive Model Partitioning for Distributed LLM Inference Across Heterogeneous Devices.
Junda Wang, Zhaoyang Li, Qianqian Yang, Jing Li, Xiaoqiang Zhao, Wenbo Zhang
Browse the full EUC paper archive.
Junda Wang, Zhaoyang Li, Qianqian Yang, Jing Li, Xiaoqiang Zhao, Wenbo Zhang
Browse the full EUC paper archive.