Open access
Aug 2026
Design of a Multi-Tenant Real-Time Inference Framework Based on OpenStack and SR-IOV GPU Virtualization
A standards-based, multi-tenant cloud inference framework that integrates OpenStack orchestration with Single Root I/O Virtualization (SR-IOV)-enabled graphics processing unit (GPU) partitioning to achieve predictable and isolated real-time inference execution.
Rui Ma, Bingfeng Shi, Xin Ma et al.
· Journal of ICT Standardizati... · 0 citations