(Reuters) – Nvidia’s new Blackwell AI chips, which have already faced delays, have had problems with accompanying servers that overheat, leading some users to worry that They will not have enough time to get the new data centers up and running, reports said on Sunday.
The report cited sources familiar with the issue as saying that Blackwell graphics processing units overheated when connected together in a custom server rack designed by the company.
The AI chipmaker has asked its suppliers to change rack designs several times to address overheating issues, according to Nvidia (NASDAQ:) employees working on the issue, as well as customers. And the suppliers know it, the report said, without naming the suppliers.
Nvidia did not immediately respond to a request for comment outside regular business hours.
Nvidia unveiled the Blackwell chips in March and previously said they would ship in the second quarter before facing delays, likely to customers such as Meta Platforms (NASDAQ: ), Alphabet (NASDAQ: ) will affect Google and Microsoft (NASDAQ:
Nvidia’s Blackwell chip takes two squares of silicon the same size as the company’s previous offering and packs them into a single component that’s 30 times faster at tasks like delivering responses to chatbots.
