NVIDIA opens Vera Rubin architecture to OCP for AI factories
At the Open Compute Project (OCP) Global Summit in San Jose, NVIDIA announced it is contributing its Vera Rubin rack and compute tray designs to the open MGX architecture. This move provides system builders with a common foundation for next-generation AI infrastructure, supporting rack deployments up to 250kW. The updated MGX 1.2 specification includes blind-mate liquid cooling and a 5,000A…
Key points
- NVIDIA contributed Vera Rubin rack designs to the open MGX architecture for 250kW AI factories.
- NVIDIA launched open-source software components for DSX AI Factory to automate network and rack management.
- NVIDIA, Meta, Google, and AMD published open specifications for next-generation AI factory facility design.
NVIDIA also launched new open-source software components for its DSX AI Factory platform, including tools for network configuration, cluster validation, and rack management. These tools are designed to help operators deploy and maintain consistent AI factory networks with minimal manual intervention. Additionally, NVIDIA joined AMD, Google, and Meta to publish the Open Data Center Specification v0.7, a unified blueprint for facility design, power architecture, and cooling infrastructure.
Partnerships were announced with Meta, Cisco, and Visionbay to advance networking and power standards. Meta is adopting NVIDIA Spectrum-6 switches for its Vera Rubin AI factories, while NVIDIA and Cisco introduced the USFP standard for 400Gb/s-based networking fabrics. Visionbay unveiled plans for an 800V DC AI factory design to address rising power density challenges in high-density computing environments.
OCP Global Summit: Amid Ecosystem Adoption, NVIDIA Opens Vera Rubin Architecture to Help Scale AI Factories Worldwide
NVIDIA Blog · 12 October 2026
Loading the full article…
This text was published by NVIDIA Blog and written by NVIDIA Writers. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Hardware & Compute
All →- Microsoft expands Azure Maia system to multi-gigawatt deployments starting in 2027 · 1 src
- Meta says data centers are central to its AI strategy · 1 src
- NVIDIA and Microsoft launch RTX Spark laptops for AI agents on Windows · 2 src
- Intel GPU D270 offers up to 480 GB LPDDR5X memory · 1 src
- Applied Materials and Intel expand AI chipmaking collaboration at epic Center · 1 src
Comments
via GitHub Discussions