Nvidia CEO Jensen Huang delivers a keynote deal with throughout the Nvidia GTC Synthetic Intelligence Convention at SAP Heart on March 18, 2024 in San Jose, California.
Justin Sullivan | Getty Photographs
Nvidia on Monday introduced a brand new technology of synthetic intelligence chips and software program for operating synthetic intelligence fashions. The announcement, made throughout Nvidia’s developer’s convention in San Jose, comes because the chipmaker seeks to solidify its place because the go-to provider for AI corporations.
Nvidia’s share value is up five-fold and complete gross sales have greater than tripled since OpenAI’s ChatGPT kicked off the AI increase in late 2022. Nvidia’s high-end server GPUs are important for coaching and deploying giant AI fashions. Corporations like Microsoft and Meta have spent billions of {dollars} shopping for the chips.
The brand new technology of AI graphics processors is known as Blackwell. The primary Blackwell chip is named the GB200 and can ship later this 12 months. Nvidia is engaging its prospects with extra highly effective chips to spur new orders. Corporations and software program makers, for instance, are nonetheless scrambling to get their arms on the present technology of “Hopper” H100s and related chips.
“Hopper is improbable, however we want larger GPUs,” Nvidia CEO Jensen Huang mentioned on Monday on the firm’s developer convention in California.
Nvidia shares fell greater than 1% in prolonged buying and selling on Monday.
The corporate additionally launched revenue-generating software program known as NIM that can make it simpler to deploy AI, giving prospects one more reason to stay with Nvidia chips over a rising area of opponents.
Nvidia executives say that the corporate is turning into much less of a mercenary chip supplier and extra of a platform supplier, like Microsoft or Apple, on which different corporations can construct software program.
“Blackwell’s not a chip, it is the title of a platform,” Huang mentioned.
“The sellable industrial product was the GPU and the software program was all to assist folks use the GPU in several methods,” mentioned Nvidia enterprise VP Manuvir Das in an interview. “After all, we nonetheless try this. However what’s actually modified is, we actually have a industrial software program enterprise now.”
Das mentioned Nvidia’s new software program will make it simpler to run packages on any of Nvidia’s GPUs, even older ones that could be higher suited to deploying however not constructing AI.
“For those who’re a developer, you have received an attention-grabbing mannequin you need folks to undertake, in the event you put it in a NIM, we’ll guarantee that it is runnable on all our GPUs, so that you attain lots of people,” Das mentioned.
Meet Blackwell, the successor to Hopper
Nvidia’s GB200 Grace Blackwell Superchip, with two B200 graphics processors and one Arm-based central processor.
Each two years Nvidia updates its GPU structure, unlocking an enormous bounce in efficiency. Lots of the AI fashions launched over the previous 12 months have been skilled on the corporate’s Hopper structure — utilized by chips such because the H100 — which was introduced in 2022.
Nvidia says Blackwell-based processors, just like the GB200, provide an enormous efficiency improve for AI corporations, with 20 petaflops in AI efficiency versus 4 petaflops for the H100. The extra processing energy will allow AI corporations to coach larger and extra intricate fashions, Nvidia mentioned.
The chip consists of what Nvidia calls a “transformer engine particularly constructed to run transformers-based AI, one of many core applied sciences underpinning ChatGPT.
The Blackwell GPU is giant and combines two individually manufactured dies into one chip manufactured by TSMC. It can even be accessible as a whole server known as the GB200 NVLink 2, combining 72 Blackwell GPUs and different Nvidia components designed to coach AI fashions.
Nvidia CEO Jensen Huang compares the dimensions of the brand new “Blackwell” chip versus the present “Hopper” H100 chip on the firm’s developer convention, in San Jose, California.
Nvidia
Amazon, Google, Microsoft, and Oracle will promote entry to the GB200 by way of cloud companies. The GB200 pairs two B200 Blackwell GPUs with one Arm-based Grace CPU. Nvidia mentioned Amazon Net Providers would construct a server cluster with 20,000 GB200 chips.
Nvidia mentioned that the system can deploy a 27-trillion-parameter mannequin. That is a lot bigger than even the most important fashions, corresponding to GPT-4, which reportedly has 1.7 trillion parameters. Many synthetic intelligence researchers consider larger fashions with extra parameters and information may unlock new capabilities.
Nvidia did not present a value for the brand new GB200 or the techniques it is utilized in. Nvidia’s Hopper-based H100 prices between $25,000 and $40,000 per chip, with entire techniques that price as a lot as $200,000, in accordance with analyst estimates.
Nvidia may even promote B200 graphics processors as a part of a whole system that takes up a whole server rack.
Nvidia inference microservice
Nvidia additionally introduced it is including a brand new product named NIM, which stands for Nvidia Inference Microservice, to its Nvidia enterprise software program subscription.
NIM makes it simpler to make use of older Nvidia GPUs for inference, or the method of operating AI software program, and can enable corporations to proceed to make use of the a whole lot of tens of millions of Nvidia GPUs they already personal. Inference requires much less computational energy than the preliminary coaching of a brand new AI mannequin. NIM permits corporations that wish to run their very own AI fashions, as an alternative of shopping for entry to AI outcomes as a service from corporations like OpenAI.
The technique is to get prospects who purchase Nvidia-based servers to join Nvidia enterprise, which prices $4,500 per GPU per 12 months for a license.
Nvidia will work with AI corporations like Microsoft or Hugging Face to make sure their AI fashions are tuned to run on all appropriate Nvidia chips. Then, utilizing a NIM, builders can effectively run the mannequin on their very own servers or cloud-based Nvidia servers with out a prolonged configuration course of.
“In my code, the place I used to be calling into OpenAI, I’ll substitute one line of code to level it to this NIM that I received from Nvidia as an alternative,” Das mentioned.
Nvidia says the software program may even assist AI run on GPU-equipped laptops, as an alternative of on servers within the cloud.
