STAO: Adaptive spatio-temporal orchestration for efficient and QoS-aware DNN inference on GPU

Shaoxun Wang, Xingjun Zhang, Kun Xia, Jiawei Cao, Tongchao Miao. STAO: Adaptive spatio-temporal orchestration for efficient and QoS-aware DNN inference on GPU. Future Generation Comp. Syst., 186:108734, 2027. [doi]

Abstract

Abstract is missing.