NVIDIA announces opening Vera Rubin architecture for AI factories
🎧 Listen to this story
At the OCP Global Summit, NVIDIA announced contributions of Vera Rubin architecture rack and compute-tray designs to the Open Compute Project (OCP) through the open NVIDIA MGX architecture. The company said the initiative provides a common foundation for manufacturers developing AI factories and includes standards for design, grid resilience and rack infrastructure.
The MGX 1.2 specification adds rack-scale liquid cooling, interoperable interconnect infrastructure and a 5,000A busbar, and supports deployments of up to 250kW per rack, NVIDIA said. The company also presented a Vera CPU rack for AI-agent tasks such as tool calling and orchestration, and announced advances with Meta, Cisco and Google in networking, modules and data transport.
Why it matters · editorial interpretation
The contribution to OCP could give manufacturers a common foundation for designing AI-factory racks and infrastructure, while the MGX 1.2 specification addresses cooling, interconnects and loads of up to 250 kW per rack, according to NVIDIA. Including agent tasks also links the architecture to infrastructure for orchestration and tool calling.
Sources
Hardware