NVIDIA Vera Rubin Ramps Into Full Production for Agentic AI Factories

NVIDIA said its Vera Rubin platform moved into full production to support agentic AI factories. The company positioned the effort around deploying a rack-scale system approach for workloads that use multi-step reasoning, retrieval, tool use and response generation.

NVIDIA linked the ramp to manufacturing by server makers and supply chain partners, including deployments across hundreds of factories and multiple countries. It also described the platform as an integrated design that combines compute, networking and security capabilities at the POD scale.

Vera Rubin was described as unifying NVIDIA Vera Rubin NVL72 systems, NVIDIA Vera CPU, NVIDIA Groq 3 LPX, NVIDIA Vera BlueField-4 STX storage, and NVIDIA Spectrum-6 SPX Ethernet racks into a fully integrated system. NVIDIA said it delivers 10x agent throughput at scale compared with the previous-generation NVIDIA Grace Blackwell platform, and that it encrypts data across high-speed interconnects as part of NVIDIA Confidential Computing, including hardware-level attestation.

NVIDIA said Vera Rubin marked the third generation of NVIDIA MGX rack-scale systems, using a proven open source MGX design. It listed partners including Dell Technologies, HPE, Lenovo, Supermicro, ASUS, Cloudian, DDN, NetApp, Nutanix, Quanta Cloud Technology (QCT), Wistron and Wiwynn, and said production shipments are set to begin starting this fall. The company added that NVIDIA Spectrum-X Ethernet Photonics, built on co-packaged optics and now in production, and NVIDIA BlueField-4 DPUs were integrated into the platform, with NVIDIA DOCA software providing multi-tenant network isolation, zero-trust policy enforcement, runtime threat detection and end-to-end encryption at speeds of up to 800Gb/s.

“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 CEO 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.”