Digital Event Horizon
Nvidia has announced several new AI-accelerating chips, including the highly anticipated "Rubin Ultra" and "Feynman" chips. The company's CEO Jensen Huang revealed these future-proof AI chips at Nvidia's GTC 2025 conference in San Jose, California, promising to revolutionize the field of artificial intelligence. These new chips are expected to deliver significant performance improvements over existing models, paving the way for more powerful and efficient AI applications.
Nvidia announces new AI-accelerating chips, including Rubin Ultra and Feynman.Vera Rubin GPU to be released in 2026 with tens of terabytes of memory.Rubin Ultra to follow in 2027 with individual GPUs and 100 petaflops of FP4 precision per chip.Blackwell Ultra B300 to launch in 2025 with 15 petaflops of dense FP4 compute performance.Feynman next-generation GPU architecture expected in 2028 with a "Vera" CPU.
Nvidia, a leading manufacturer of graphics processing units (GPUs), has recently announced several new AI-accelerating chips that promise to revolutionize the field of artificial intelligence. At Nvidia's GTC 2025 conference in San Jose, California, CEO Jensen Huang revealed the company's plans for its future AI chips, including the highly anticipated "Rubin Ultra" and "Feynman" chips.
The centerpiece announcement was the Vera Rubin GPU, scheduled for release in the second half of 2026. This GPU will feature tens of terabytes of memory and come equipped with a custom Nvidia-designed CPU called Vera. According to Nvidia, Vera Rubin will deliver significant performance improvements over its predecessor, Grace Blackwell, particularly for AI training and inference.
Specifications for Vera Rubin, presented by Jensen Huang during his GTC 2025 keynote, revealed that the GPU features two GPUs together on one die that deliver 50 petaflops of FP4 inference performance per chip. When configured in a full NVL144 rack, the system delivers 3.6 exaflops of FP4 inference compute—3.3 times more than Blackwell Ultra's 1.1 exaflops in a similar rack configuration.
In addition to Vera Rubin, Nvidia also announced Rubin Ultra, which will follow in the second half of 2027. Rubin Ultra will use the NVL576 rack configuration and feature individual GPUs with four reticle-sized dies, delivering 100 petaflops of FP4 precision (a 4-bit floating-point format used for representing and processing numbers within AI models) per chip.
At the rack level, Rubin Ultra will provide 15 exaflops of FP4 inference compute and 5 exaflops of FP8 training performance—about four times more powerful than the Rubin NVL144 configuration. Each Rubin Ultra GPU will include 1TB of HBM4e memory, with the complete rack containing 365TB of fast memory.
For the near future, Nvidia will launch Blackwell Ultra B300 in the second half of 2025. This chip features two GPUs delivering 15 petaflops of dense FP4 compute performance per chip. When configured in a full NVL72 rack, Blackwell Ultra will provide 1.1 exaflops of dense FP4 inference compute—1.5 times more than the current Blackwell B200 configuration.
Lastly, Nvidia briefly mentioned a next-generation GPU architecture called "Feynman," named after American theoretical physicist Richard Feynman. He provided few additional details about Feynman's design or capabilities, only that it would use a "Vera" CPU instead of the expected "Richard" based on the naming pattern and that it would arrive sometime in 2028.
In a broader context, Nvidia CEO Jensen Huang emphasized his vision for the future of AI, where he called data centers "AI factories" that produce tokens (the units of data that AI models currently process) instead of physical objects. He shared his enthusiasm for the potential of AI to power humanoid robots to perform human-like labor.
Furthermore, Huang speculated that Nvidia chips will soon power "10 billion digital agents" that perform helpful work for humans, and he mentioned that by the end of this year, 100 percent of Nvidia engineers will be assisted by AI models. These predictions underscore Nvidia's commitment to pushing the boundaries of artificial intelligence and further solidify its position as a leader in the field.
Related Information:
https://www.digitaleventhorizon.com/articles/Nvidia-Unveils-Future-Proof-AI-Chips-A-New-Era-for-Artificial-Intelligence-deh.shtml
https://arstechnica.com/ai/2025/03/nvidia-announces-rubin-ultra-and-feynman-ai-chips-for-2027-and-2028/
Published: Tue Mar 18 19:53:22 2025 by llama3.2 3B Q4_K_M
