Nvidia’s new Blackwell AI chips, which have already faced delays, have now encountered problems with accompanying servers that overheat. It has caused some customers to worry as they will not have enough time to get new data centers up and running.
The AI chips are facing overheating issues when they are connected to server racks the company has designed, causing potential delays for customers setting up data centers.
As per The Indian Express, server racks are designed to hold up to 72 chips, citing sources familiar with the issue. According to the Nvidia employees who have been working on the issues, the AI chipmaker’s, customers and suppliers with knowledge of it have asked its suppliers to change the design of the racks several times to resolve overheating problems, the report said without naming the suppliers.
The company’s spokesperson said in a statement to Reuters that, “Nvidia is working with leading cloud service providers as an integral part of our engineering team and process. The engineering iterations are normal and expected”.
In March, Nvidia identified Blackwell chips and had earlier said that they would ship in the second quarter before encountering delays, potentially affecting customers such as Meta Platforms (META. O), opens new tab, Alphabet’s (GOOGL. O), opens new tab Google and Microsoft (MSFT. O), opens new tab.
Nvidia’s Blackwell chip takes two squares of silicon the size of the company’s previous offering and binds them into a single component that is 30 times speedier at tasks like providing responses from chatbots.
Also Read: Nvidia’s New AI Chips Delayed, Affecting Google, Microsoft, Meta
