Search results for Groq 3 LPX
AI & Enterprise
Nvidia begins mass production of Groq 3 LPX for AI agents
Nvidia has shifted its Groq 3 LPX inference accelerator for AI agents into mass production. The chip extends Nvidia\'s Vera Rubin data center platform and targets high-speed token generation to reduce decode latency in agent workflows. In an Artificial Analysis benchmark, it produced 3,400 tokens per second running the open-source Gemma 4 31B model with a 100,000-token context window. Nebius Group is among early adopters, and SpaceX was named a new flagship customer.
Industry
From GPUs to factory floors, Nvidia redefines manufacturing landscape
At GTC 2026, Nvidia rolled out multiple chips, racks and software, highlighting three shifts: changes in AI computing cost structures, new software monetisation models and deeper AI adoption in manufacturing and mobility. It presented the Vera Rubin platform, the Groq 3 LPX inference rack and a 100 trillion dollar estimate for the physical AI market. It also cited expanding infrastructure deployment and the role of Korean suppliers including Samsung and SK Hynix.
AI & Enterprise
Tech Insight: Nvidia is now an AI infrastructure platform company
Nvidia is now a heterogeneous AI infrastructure platform company, tech analyst Patrick Moorhead said after hearing announcements at Nvidia\'s annual GTC 2026 conference. Nvidia unveiled its new Vera Rubin AI infrastructure platform, including chips and rack systems designed for mass production. It also highlighted integration with Groq inference hardware and growing demand for its Vera CPU. Nvidia detailed software moves with Dynamo 1.0 and a security-enhanced NeMo stack, and cited adoption across cloud, enterprise and robotics.
