Taming GPU Inference Variability with Risk-Aware Scheduling and Dynamic Kernel Segments

Mingyuan Ding, Guangping Xu, Kang Liu, Junhui Li, Lei Yang, Yunjie Li. Taming GPU Inference Variability with Risk-Aware Scheduling and Dynamic Kernel Segments. In IEEE/ACM International Symposium on Quality of Service, IWQoS 2026, Istanbul, Turkiye, June 29 - July 2, 2026. pages 1-10, IEEE, 2026. [doi]

Abstract

Abstract is missing.