Nvidia said on 21 October that Google Cloud will make Vera Rubin-based A5X instances generally available in November, with availability also planned for Europe. Google Cloud plans to scale the infrastructure to as many as 960,000 Rubin GPUs across multiple sites. The instances combine Nvidia Vera Rubin NVL72 systems and ConnectX-9 SuperNICs with Google Cloud’s Virgo Network and fourth-generation liquid cooling for training, inference and large-scale reinforcement learning.
Nvidia said Ineffable Intelligence, a London-based company founded by AlphaGo creator David Silver, was the first customer to access A5X and is using it for reinforcement learning research. WPP also demonstrated a creative-agent design on A5X using Nvidia Nemotron models and OpenShell. In WPP’s initial tests, Nvidia said, workloads that typically needed a multi-node cluster ran on one A5X instance.
Google Cloud will also offer Nvidia Confidential Computing on bare-metal A4X Max instances powered by GB300 NVL72, Nvidia said. The companies are exploring DSX MaxLPS capabilities for the Vera Rubin infrastructure to improve performance per watt.
