The NVIDIA Rubin platform represents a fundamental shift from accelerator-centric design to rack-scale AI factory architectures using co-design to tightly integrate CPUs, GPUs, DPUs, NVLink fabrics, and high-speed Spectrum-X Ethernet networking. BlueField-4 extends this architecture by offloading networking, storage, security, and infrastructure services from host CPUs, creating a programmable operating layer for AI at scale. The BlueField-4 data storage processor fuels a new tier of fast, efficient KV cach ...

Core Viewpoint - CoreWeave, Inc. announced the integration of NVIDIA Rubin technology into its AI cloud platform, enhancing its offerings for customers focused on agentic AI, reasoning, and large-scale inference workloads [1] Group 1: Company Developments - CoreWeave is expected to be one of the first cloud providers to implement the NVIDIA Rubin platform in the second half of 2026, which will provide customers with increased flexibility and choice [1]

RALEIGH, N.C.--(BUSINESS WIRE)--Red Hat, the world's leading provider of open source solutions, today announced a landmark expansion of its collaboration with NVIDIA to align enterprise open source technologies to the rapidity of enterprise AI evolution and rack-scale AI advances. As the industry moves beyond individual servers toward unified, high-density systems, Red Hat aims to deliver the starting point for this transformation with Red Hat Enterprise Linux for NVIDIA, a specialized edition of the world' ...

News Summary: The Rubin platform harnesses extreme codesign across hardware and software to deliver up to 10x reduction in inference token cost and 4x reduction in number of GPUs to train MoE models, compared with the NVIDIA Blackwell platform.NVIDIA Spectrum-X Ethernet Photonics switch systems deliver 5x improved power efficiency and uptime.New NVIDIA Inference Context Memory Storage Platform with NVIDIA BlueField-4 storage processor to accelerate agentic AI reasoning.Microsoft’s next-generation Fairwater ...