Nvidia Says SpaceXAI Will Deploy Vera CPU and Extend Vera Rubin to Orbital Computing

On Aug. 24, Nvidia said SpaceXAI will deploy its Vera CPU to accelerate next-generation agentic AI applications. Nvidia said Vera is the first CPU built specifically for AI agents. The chip uses 88 in-house Olympus cores, spatial multithreading technology and LPDDR5X high-bandwidth memory, delivering 1.2 TB/s of bandwidth. The company said Vera can improve task completion speed by up to 1.8 times versus x86 CPUs in agentic AI, reinforcement learning and data processing workloads. SpaceXAI President Mike Nicolls said Vera’s CPU performance and memory bandwidth are sufficient for large-scale task orchestration, code execution and data processing, while helping GPUs stay as efficient as possible and extracting more useful output per watt of computing. SpaceXAI also plans to expand the AI infrastructure behind Grok using Nvidia’s Vera Rubin platform and move toward gigawatt-scale compute capacity. Vera Rubin combines Nvidia accelerated computing, NVLink interconnect, Spectrum-X networking and BlueField data processing technology. Nvidia said the platform is designed to reduce per-token cost and improve overall AI factory efficiency. More notably, SpaceXAI will send an optimized Vera Rubin NVL72 system into space. Its first-generation Starmind AI satellite will use the rack-scale architecture, marking what Nvidia called its first landmark deployment extending accelerated computing from terrestrial data centers to orbital computing.