NVIDIA releases Vera Rubin DSX AI Factory design and Omniverse DSX Blueprint with industry collaboration

NVIDIA introduced the Vera Rubin DSX Artificial Intelligence (AI) Factory reference design alongside the generally available Omniverse DSX Blueprint, tools aimed at guiding and simulating AI infrastructure management. These developments focus on improving efficiency in token generation per watt and shortening the path to initial production for AI factory operations.

The reference design outlines a comprehensive approach to building integrated AI infrastructure that spans compute, networking, storage, power, cooling, and control systems. It supports scalable cluster performance while documentation offers design and operational guidance. The software stack connects hardware components across power and cooling domains to optimize energy use with modular flexibility.

The Omniverse DSX Blueprint serves as a fully compatible framework for creating detailed digital twins of AI factories. It integrates power, cooling, networking, and operations into a unified simulation environment to facilitate design validation, operational rehearsal, and performance optimization before physical deployment.

Multiple organizations are contributing to the DSX architecture, supplying simulation-ready models, software integrations, and infrastructure components. Contributors include Cadence, Dassault Systèmes, Eaton, Jacobs, NScale, Phaidra, Procore Technologies, PTC, Schneider Electric, Siemens, Switch, Trane Technologies, and Vertiv. Energy firms such as Emerald AI, GE Vernova, Hitachi, and Siemens Energy are leveraging the reference architecture to enhance grid capacity and supply power for AI factory setups.

Jensen Huang, founder and CEO of NVIDIA, said, “In the age of AI, intelligence tokens are the new currency, and AI factories are the infrastructure that generates them. With the NVIDIA Vera Rubin DSX AI Factory reference design and Omniverse DSX Blueprint, we are providing the foundation to build the world’s most productive AI factories, accelerating time to first revenue and maximizing scale and energy efficiency.”

The companies involved outlined plans to further integrate these tools with various platforms and solutions to aid in planning, building, and operating large-scale AI infrastructure. These efforts include enhancing simulation capabilities, optimizing power distribution, and reducing energy consumption in cooling systems.