Milind Varma, Sai Venkat Malreddy, Liting Hu. DNN-Adapt: Reinforcement Learning-Based Hybrid Batching for Efficient DNN Serving. In Rong N. Chang, Carl K. Chang, Jingwei Yang, Nimanthi Atukorala, Dan Chen, Sumi Helal, Sasu Tarkoma, Qiang He 0001, Tevfik Kosar, Claudio A. Ardagna, Feras Awaysheh, Volker Hilt, Yogesh Simmhan, editors, 18th IEEE International Conference on Cloud Computing, CLOUD 2025, Helsinki, Finland, July 7-12, 2025. pages 451-453, IEEE, 2025. [doi]
Abstract is missing.