NVIDIA announces Vera is shipping at scale, with AWS receiving the first Vera CPU server and Vera Rubin GPU
Following·since 25 Aug 2026·Day 8·2 sources
Nvidia Vera CPU ships at scale; AWS is the first cloud recipient
The gist
NVIDIA is entering the standalone CPU market, which it describes as a $200 billion opportunity, by targeting the orchestration layer of agentic AI systems. AWS adoption and an independent benchmark provide early signals on deployment and competitive positioning.
The full picture
NVIDIA's Vera CPU is now shipping at scale, with AWS receiving the first Vera CPU server and Vera Rubin GPU. The chip targets CPU-side tasks in agentic AI pipelines, including Python execution, tool calls, retrieval, orchestration, and sandboxed code execution. Vera carries 88 custom Olympus cores and up to 1.2 TB/s memory bandwidth. NVIDIA claims up to 1.8x faster performance on selected agentic workloads compared to x86 CPUs. Independent Phoronix testing put Vera 10% ahead of AMD EPYC 9575F on the geometric mean, though NVIDIA restricted the test suite to Vera-relevant workloads. SpaceXAI has announced it will use Vera to accelerate Grok's agentic systems, and plans to run an optimized version of Vera hardware aboard an AI satellite called Starmind.
How it developed
SpaceXAI announces use of Vera CPU for Grok's agentic systems and the Starmind AI satellite
Sources
Rohan Paul Twitter
The daily email
Want this in your inbox?
I send a short email each morning with the stories that moved. If you would rather just read here, that works too.
Subscribe free