SpaceXAI Deploys NVIDIA Vera CPU for Agentic AI Workloads

NVIDIA said SpaceXAI will deploy NVIDIA Vera CPUs to accelerate work for next-generation agentic AI applications. The move connects CPU-focused orchestration for AI systems with plans to scale compute capacity and extend that approach beyond terrestrial data centers.

As SpaceXAI expands its AI infrastructure for Grok, NVIDIA said Vera Rubin provides a common architecture for scaling. The company also described plans to adapt an optimized Vera Rubin NVL72 system for use in SpaceXAI’s first-generation Starmind AI satellite.

NVIDIA characterized Vera as a CPU built for AI agents, targeting CPU-intensive workloads around model inference, including tool use, code execution, data processing, orchestration and simulation. NVIDIA said Vera includes 88 NVIDIA-designed Olympus cores, NVIDIA Spatial Multithreading technology, and high-bandwidth LPDDR5X memory, with up to 1.2TB/s of bandwidth.

NVIDIA said Vera Rubin brings together NVIDIA accelerated computing with NVIDIA NVLink interconnect technology, NVIDIA Spectrum-X Ethernet networking, NVIDIA BlueField data processing and NVIDIA software. It said the platform is codesigned across compute, networking and software to optimize an AI factory as a whole, and that SpaceXAI plans to extend an adapted version beyond Earth. “Agentic AI requires a new kind of computing system — one built not only to generate answers, but to take action,” Ian Buck said. “Vera gives AI agents the CPU performance to act in real time — executing code, processing data and coordinating complex tasks,” he said. “Vera gives us the CPU performance and memory bandwidth to run enormous amounts of orchestration, code and data processing while keeping GPUs doing what they do best,” Mike Nicolls said.

Provided by Globe Newswire on behalf of Nvidia. Read the original.