Towards Fair and Firm Real-Time Scheduling in DNN Multi-Tenant Multi-Accelerator Systems via Reinforcement Learning

arXiv:2403.00766v1 Announce Type: cross
Abstract: This paper addresses the critical challenge of managing Quality of Service (QoS) in cloud services, focusing on the nuances of individual tenant expectations and varying Service Level Indicators (SLIs). It introduces a novel approach utilizing Deep Reinforcement Learning for tenant-specific QoS management in multi-tenant, multi-accelerator cloud environments. The chosen SLI, deadline hit rate, allows clients to tailor QoS for each service request. A novel online scheduling algorithm for Deep Neural Networks in multi-accelerator systems is …

abstract accelerator arxiv challenge cloud cloud services cs.ar cs.dc cs.lg dnn fair novel paper quality real-time reinforcement reinforcement learning scheduling service services systems type via