Presentation
RELMAS-HRT: Online Inference Scheduling in Mixed-Criticality Multi-Tenant Multi-Accelerator Systems via Reinforcement Learning
DescriptionWe present RELMAS-HRT, an online reinforcement learning scheduler for heterogeneous multi-accelerator systems (MAS) that guarantees hard real-time (HRT) deadlines while optimizing QoS for multi-tenant DNN inference. The framework admits HRT tasks through a WCET-based feasibility test, constructs a deterministic baseline schedule, and dynamically refines it at runtime using an RL policy whose decisions are accepted only when provably safe. RELMAS-HRT exploits slack and missing HRT releases to improve QoS-aware throughput without compromising guarantees. Experiments show 100% HRT deadline satisfaction and higher QoS adherence with respect to baselines policies, enabling efficient mixed-criticality inference in industrial systems.
Event Type
Work in Progress
TimeMonday, July 276:35pm - 6:35pm PDT
LocationExhibit Hall
Similar Presentations