At GTC, Jensen Huang offered the first details on the company’s upcoming datacenter hardware to succeed Grace and Blackwell.
Building out the datacenters—or as NVIDIA calls them, « AI factories »—required for training and operating state-of-the-art AI models is extremely expensive. So much so that even hyperscalers like Google and Microsoft are going to have to plan these purchases well in advance. To that end, NVIDIA offered a sneak peek of its upcoming products at today’s GTC opening keynote, and you might want to sit down for this one.The company’s extant Blackwell processors are most optimally deployed in the form of « NVL72 » racks. These are full racks that are fully integrated using high-speed NVLink interconnects such that the entire rack can be treated as a single GPU. The « 72 » in the name comes from the number of individual Blackwell GPUs in the rack. Well, NVIDIA’s next-gen parts are going to be called Vera Rubin NVL144. That means twice as many GPUs, right?No, actually. Jensen apologized on stage, but the company is actually changing the way it counts this figure with the next generation.
