Nvidia Corporation, an American multinational corporation and technology company, unveiled its most powerful artificial intelligence (AI) graphics platform and software for running AI models at a developer conference in San Jose, California, on Monday.
The US chipmaker’s new AI computing platform is called Blackwell and is the successor to Hopper, and the first chip of the GB200 platform will be available later this year. Nvidia CEO Jensen Huang declared:
“Hopper is fantastic, but we need bigger GPUs. Accelerated computing has reached the tipping point — general-purpose computing has run out of steam. We need another way of doing computing so that we can continue to scale, so that we can continue to drive down the cost of computing.”
Huang believes that accelerated computing would significantly speed up work in every single industry. The amount of energy and time saved would be “tremendous,” he added.
The way we compute is fundamentally different. We created a processor for the generative AI era.
He stated that generative AI changed the way applications were written, adding that with Nvidia’s new NIM software, customers could use off-the-shelf NIM microservices, with Nvidia being able to help “build proprietary AI and copilots.”
