All articles tagged with #rubin
Nvidia says it has restarted manufacturing of its H200 chip, designed to comply with U.S. export restrictions on China, after receiving export licenses; production had been paused last year amid regulatory hurdles, and the company is ramping up supply as it pursues more than $1 trillion in revenue from its Blackwell and Rubin AI chips by 2027, with Rubin and Blackwell in production and Groq tech licensed.
Meta expands its Nvidia partnership by ordering millions of Blackwell and Rubin GPUs and CPUs in a multibillion-dollar deal to boost AI inference in Meta’s data centers, reinforcing Nvidia’s lead in AI chips and easing concerns about Broadcom or Google’s TPUs eroding share. Meta will also integrate Nvidia Spectrum-X switches; pricing wasn’t disclosed, and analysts see Nvidia continuing to gain momentum as hyperscalers push full-stack silicon and networking solutions.
Nvidia has announced its new AI chip architecture, Rubin, just months after unveiling the Blackwell model, highlighting the company's accelerated pace in AI chip development. CEO Jensen Huang introduced Rubin ahead of the COMPUTEX tech conference, emphasizing Nvidia's commitment to a "one-year rhythm" for new chip releases. This rapid advancement underscores the competitive intensity in the AI chip market, with rivals like AMD, Intel, and major tech companies striving to catch up. The Rubin platform will feature new GPUs and a central processor named Vera.
Nvidia CEO Jensen Huang announced that the company's next-generation AI chip platform, named Rubin, will be launched in 2026. The Rubin family will include new GPUs, CPUs called Versa, and networking chips, featuring high-bandwidth memory from SK Hynix, Micron, and Samsung. Nvidia plans to release a new family of AI chips annually, accelerating from its previous biennial schedule.
NVIDIA has unveiled its next-gen Rubin GPU architecture, along with Rubin and Blackwell GPUs and the latest Vera CPU. The Rubin GPUs, expected to be mass-produced by late 2025, will feature HBM4 memory and a 4x reticle design. The Blackwell GPUs will launch in 2024, followed by an Ultra version in 2025. The Vera CPU, based on TSMC's 3nm process, will be part of the GR200 Superchip module. NVIDIA aims to enhance power efficiency and AI capabilities with these new products.