Nvidia CEO Jensen Huang delivers a keynote handle through the Nvidia GTC Synthetic Intelligence Convention at SAP Middle on March 18, 2024 in San Jose, California.
Justin Sullivan | Getty Pictures
Nvidia on Monday introduced a brand new era of synthetic intelligence chips and software program for working 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 firms.
Nvidia’s share value is up five-fold and complete gross sales have greater than tripled since OpenAI’s ChatGPT kicked off the AI growth in late 2022. Nvidia’s high-end server GPUs are important for coaching and deploying massive AI fashions. Firms like Microsoft and Meta have spent billions of {dollars} shopping for the chips.
The brand new era of AI graphics processors is called Blackwell. The primary Blackwell chip is named the GB200 and can ship later this yr. Nvidia is attractive its clients with extra highly effective chips to spur new orders. Firms and software program makers, for instance, are nonetheless scrambling to get their arms on the present era of “Hopper” H100s and related chips.
“Hopper is incredible, however we’d like greater 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 clients another excuse to stay with Nvidia chips over a rising subject of rivals.
Nvidia executives say that the corporate is changing into much less of a mercenary chip supplier and extra of a platform supplier, like Microsoft or Apple, on which different firms can construct software program.
“Blackwell’s not a chip, it is the identify 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. “In fact, we nonetheless do 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 is perhaps higher suited to deploying however not constructing AI.
“For those who’re a developer, you’ve got obtained an attention-grabbing mannequin you need folks to undertake, when 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 a giant leap in efficiency. Lots of the AI fashions launched over the previous yr had been educated 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 firms, with 20 petaflops in AI efficiency versus 4 petaflops for the H100. The extra processing energy will allow AI firms to coach greater and extra intricate fashions, Nvidia mentioned.
The chip contains 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 massive and combines two individually manufactured dies into one chip manufactured by TSMC. It’s going to even be accessible as a complete server known as the GB200 NVLink 2, combining 72 Blackwell GPUs and different Nvidia elements 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 Internet 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, reminiscent of GPT-4, which reportedly has 1.7 trillion parameters. Many synthetic intelligence researchers imagine greater fashions with extra parameters and information might unlock new capabilities.
Nvidia did not present a value for the brand new GB200 or the programs it is utilized in. Nvidia’s Hopper-based H100 prices between $25,000 and $40,000 per chip, with complete programs that price as a lot as $200,000, in line with analyst estimates.
Nvidia will even promote B200 graphics processors as a part of an entire system that takes up a complete 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 working AI software program, and can permit firms 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 firms that wish to run their very own AI fashions, as an alternative of shopping for entry to AI outcomes as a service from firms like OpenAI.
The technique is to get clients who purchase Nvidia-based servers to join Nvidia enterprise, which prices $4,500 per GPU per yr for a license.
Nvidia will work with AI firms 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 no prolonged configuration course of.
“In my code, the place I used to be calling into OpenAI, I’ll change one line of code to level it to this NIM that I obtained from Nvidia as an alternative,” Das mentioned.
Nvidia says the software program will even assist AI run on GPU-equipped laptops, as an alternative of on servers within the cloud.