At Mobile World Congress (MWC) 2025, MEF, Infosys, NVIDIA, and IronYun unveiled a GPU-as-a-Service (GPUaaS) for AI at the Edge initiative, demonstrating how service providers can monetize network infrastructure by delivering real-time AI inferencing at the Edge. Powered by MEF’s Lifecycle Service Orchestration (LSO) APIs, the solution enables enterprises to seamlessly order and deploy high-performance GPU resources for AI applications, reducing latency and enhancing real-time processing capabilities. The demonstration highlights new revenue opportunities for network providers, while ensuring standardized, scalable AI solutions for enterprises.
By leveraging MEF’s API framework, Infosys has developed an automated, seamless ordering process that integrates AI workloads with service provider networks, simplifying deployment and accelerating AI adoption at the Edge. IronYun showcased its Vaidio AI Vision Platform, demonstrating real-world applications such as video analytics for security, safety, and intelligent traffic management. Traditional cloud-based AI processing often introduces latency, making Edge computing essential for real-time AI workloads. With MEF’s Edge Compute Infrastructure-as-a-Service (IaaS) standard, Cloud Service Providers and Subscribers can now standardize and compare Edge GPU offerings, unlocking new AI-driven business models.
The initiative marks a major milestone in AI-powered networks, expanding MEF’s standardized framework to include on-demand GPU resources for AI inferencing. Service providers can now deliver low-latency AI solutions across multiple sectors, from enterprise security to industrial automation. With MEF’s LSO APIs ensuring interoperability, GPUaaS simplifies AI workload orchestration, reduces operational complexity, and drives greater efficiency in AI deployment at scale.
• MEF, Infosys, NVIDIA, and IronYun demonstrate GPU-as-a-Service for AI at the Edge at MWC 2025.
• MEF’s LSO APIs enable seamless, automated ordering and activation of Edge GPU resources.
• Infosys integrates AI workloads with service provider networks for real-time AI inferencing.
• IronYun showcases real-world AI applications, including video analytics for security and safety.
• MEF’s Edge Compute IaaS standard expands to include GPUaaS, enabling new monetization models for AI-powered networks.
“This initiative is a major leap forward in AI at the provider edge,” said Pascal Menezes, CTO, MEF. “By enabling service providers to offer GPU-as-a-Service, we are empowering enterprises to run AI inferencing at the Edge with greater scalability and efficiency. With this announcement, MEF, Infosys, NVIDIA, and IronYun are setting a new benchmark for AI services, paving the way for a future where AI at the Edge is seamlessly accessible, scalable, and monetizable.”
