Nvidia Corp. co-founder and CEO Jensen Huang attends the Nvidia GPU Technology Conference (GTC) in San Jose, California, USA, Tuesday, March 19, 2024.
David Paul Morris | Bloomberg | Getty Images
Nvidia on Sunday unveiled its next-generation artificial intelligence chip, a successor to an older model unveiled just a few months ago, in March.
Nvidia CEO Jensen Huang unveiled a new AI chip architecture called “Rubin” ahead of the COMPUTEX tech conference in Taipei.
Rubin's announcement comes a few months after unveiling the next-generation Blackwell model in March, which is still in production and scheduled to ship to customers in the second half of 2024.
Huang's announcement of Rubin is likely to further accelerate the company's already accelerated pace of progress in AI chips.
Nvidia has committed to releasing new AI chip models on a “one-year cadence,” as Huang put it on Sunday. The company has previously slowed its chip refresh schedule to two years.
The switch from Blackwell to Rubin took less than three months, but it highlights the fierce competition in the AI chip market and Nvidia's aggressive push to maintain its leading position.
AMD and Intel are two major competitors that are trying to catch up, but their gross margins fell behind Nvidia's in the most recent quarters. Companies like Microsoft, Google and Amazon are also vying for the top spot, despite being Nvidia's largest customers. A number of startups are also trying to get into the space.
“We are at a major inflection point in computing,” Huang said Sunday. “With our innovations in AI and accelerated computing, we are pushing the boundaries of what's possible and driving the next wave of technological advancements.”
The Rubin chip platform will feature a new GPU, a key graphics processing technology that helps train and power AI systems, and other new features, including a central processor called “Vera,” though Sunday's announcement didn't provide many details.
Nvidia shares were roughly flat at the close on Friday, trading at $1,096.
