Nvidia CEO Jensen Huang personally delivered the first DGX H200 GPU to OpenAI’s Sam Altman and Greg Brockman, continuing the longstanding partnership between the two companies. This significant gesture marked the first H200 GPU release globally.
Huang’s donation of the H200 GPU to OpenAI, following its announcement in March alongside the GB200 AI super chip, carries symbolic weight. Brockman, OpenAI’s president, shared a photo with Huang, Altman, and the DGX H200 GPU, highlighting the special significance of its delivery by Huang himself. Huang’s message during the donation, according to Brockman, was “to advance AI, computing, and humanity.”
OpenAI, a renowned research organization focused on artificial intelligence, has played a pivotal role in the development of AI technologies. Their recent launch of ChatGPT, a conversational AI model, has generated immense interest in the field.
As a successor to the popular H100 GPU, the DGX H200 GPU offers enhanced capabilities, including 1.8 times the memory and 1.4 times the bandwidth of its predecessor. This substantial increase in memory and bandwidth significantly accelerates information processing by reducing the need for slower external storage.
Moreover, the GB200 AI superchip, unveiled alongside the H200 GPU, boasts impressive speed, being 8,470 times faster than the DGX-1 supercomputer that Huang donated to OpenAI in 2016. Huang himself refers to it as the “miracle” chip.
This latest development further strengthens the collaboration between Nvidia and OpenAI, underscoring their shared commitment to driving innovation in the field of artificial intelligence.
