SGDRC: Software-Defined Dynamic Resource Control for Concurrent DNN Inference on NVIDIA GPUs

Open Webpage

Yongkang Zhang, Haoxuan Yu, Chenxia Han, Cheng Wang, Baotong Lu, Yunzhe Li, Zhifeng Jiang, Yang Li, Xiaowen Chu, Huaicheng Li

Published: 01 Jan 2025, Last Modified: 13 May 2025PPoPP 2025EveryoneRevisionsBibTeXCC BY-SA 4.0