Zhaoxing Wang, Xuehai Tang, Qiuyang Liu, Jizhong Han. Jily: Cost-Aware AutoScaling of Heterogeneous GPU for DNN Inference in Public Cloud. In 38th IEEE International Performance Computing and Communications Conference, IPCCC 2019, London, United Kingdom, October 29-31, 2019. pages 1-8, IEEE, 2019. [doi]
Abstract is missing.