Red Hat announced on May 11 that Zero Latency, a distributed AI inference network, has selected Red Hat AI Factory with NVIDIA as the foundation for its United States-wide neocloud infrastructure. The collaboration is designed to power real-time artificial intelligence at the edge by dispatching high-performance GPU compute across multiple locations.
The move addresses key challenges facing real-world AI applications, such as latency and data processing speed, which are especially important for industrial automation and real-time transactions. Centralized cloud architectures often struggle to meet these requirements due to latency constraints. By using a distributed network of edge datacenters, Zero Latency aims to provide standardized, high-performance environments closer to where data originates.
Zero Latency’s neocloud solution aggregates and manages AI inference from decentralized edge datacenters into industrial centers through its Zerogrid network. This system is powered by scalable low-latency nodes using NVIDIA Blackwell GPUs and runs on Intel Xeon processors. The backbone of this platform relies on Red Hat AI Enterprise and Red Hat Advanced Cluster Management for Kubernetes, allowing unified management of GPU resources across multiple sites.
Joe Fernandes, vice president and general manager of the AI Business Unit at Red Hat, said: “Zero Latency is changing how AI compute reaches the edge. By using Red Hat AI Enterprise to manage distributed infrastructure, Zero Latency highlights how hybrid cloud technologies scale innovation without the burden of extensive resource investment. We’re working with Zero Latency to help define the architecture for the future of low-latency AI applications.”
Michael Huerta, cofounder of Zero Latency, said: “We’ve believed for years that decentralized infrastructure beats centralized for the workloads that need it most. We proved that model in the power markets. AI inference is the next domain it belongs in: machine-driven, constraint-bound, and poorly served by the centralized cloud. Red Hat AI Enterprise gives us the containerization foundation to bring this architecture to enterprise customers, from the factory floor to the city street.”
Zero Latency’s initial datacenters are already operational in select locations within its U.S.-wide footprint and there are plans for expansion into hundreds more sites globally.
