Open access
Sep 2026
HARP: An Adaptive Hybrid Autoscaling Framework with Online Policy Arbitration for SLO-Aware Cloud-Native ML Inference
HARP is presented, an adaptive hybrid framework that treats the choice of control philosophy as an online decision rather than a design-time commitment and cuts SLO violations by 26.8–92.4% on three real production traces driven by a measured CPU inference profile.
Yu-Chen Luo, Zi-Han Peng, Rui Zhang
· International Journal of Adv... · 0 citations