Home
News
Nvidia ramps AI platform into production…

Nvidia ramps AI platform into production for next-generation “AI factories”

Nvidia says its Vera Rubin platform is entering full production, with global server manufacturers and cloud providers preparing to deploy the system at scale to power so-called “agentic AI factories.”

The company says Taiwan-based server makers and a wide ecosystem of global infrastructure partners are manufacturing Vera Rubin-based systems for AI labs, hyperscalers and cloud providers.

Vera Rubin is described by Nvidia as a pod-scale platform that combines multiple rack systems into a single integrated AI supercomputer designed for agentic workloads. The company says the system delivers 10 times the agent throughput of its previous-generation Grace Blackwell platform.

“Agentic AI is a new kind of workload. One prompt can launch a thousand-step journey of reasoning, retrieval, tool use and response generation,” said Jensen Huang, founder and chief executive officer of Nvidia. “Vera Rubin was built for this moment — an AI factory engine that delivers intelligence at scale, with the performance, efficiency and security needed to power the next industrial revolution.”

Nvidia says the platform is being built using its MGX rack-scale architecture and is supported by hundreds of ecosystem partners across more than 30 countries, including major server manufacturers and storage and infrastructure firms.

The system includes Nvidia’s Spectrum-X Ethernet Photonics networking technology, which the company says uses co-packaged optics to improve power efficiency and accelerate deployment timelines compared with traditional networking components.

It also integrates Nvidia’s BlueField DPUs and includes software-defined networking capabilities intended to support multi-tenant AI infrastructure at high speeds.

The company says the platform incorporates confidential computing features designed to secure data and workloads in shared cloud environments, alongside its DOCA software platform for managing security, encryption and network isolation.

Nvidia says the Vera Rubin platform is designed to support large-scale “AI factories” by integrating hardware, software and infrastructure planning through its DSX platform, which it says helps optimize deployment and operational efficiency.

Production shipments of Vera Rubin systems are expected to begin this fall.

Related Posts

Comments

Leave a Reply

Your email address will not be published. Required fields are marked *