Rubin Ultra, Huang boasted, is designed so that 576 GPU dies can be crammed into a single rack consuming 600 kW of power.

At GTC, Jensen Huang offered the first details on the company's upcoming datacenter hardware to succeed Grace and Blackwell.

Nvidia recently revealed details about its new AI graphics processors, and one of them is named for a scientist familiar to ...

Nvidia GTC Keynote ran a little long, but the content is amazing as Nvidia seeks to cement its position as the foundational ...

Jensen Huang headlined the Nvidia GTC 2025 keynote, giving updates on Blackwell, Vera Rubin, and a new Disney and Google ...

The company’s new chips are built to meet generative AI’s growing demand for real-time reasoning capabilities.

In the DGX GB300 NVL72, the number denoted the 72 GPUs in the rack. From Rubin on, it will instead show the number of reticle ...

For Hopper-based systems running Llama models, Nvidia claims Dynamo can effectively double the inference performance.

Jetson Thor Complementing Project GR00T, NVIDIA announced Jetson Thor, a new computer built specifically for humanoid robots.

We are now a power-limited industry,” he said. With AI models growing exponentially in complexity and scale, the race is on ...

Some reasoning models like OpenAI's o1 ... which means that inference must also scale up to keep up with the demand. Rubin, on the other hand, allows the AI models to distribute workloads across ...