The server rack Nvidia designed for Blackwell—which can connect up to 72 GPUs at a time—is reportedly causing the overheating issue. Nvidia has repeatedly redesigned the racks, which could result in GPU server shipments being delayed and new Google ...

Speaking to DCD earlier this year, Ian Buck, Nvidia’s accelerated computing VP, said: "The fabric of NVLink, the spine, is connecting all those 72 GPUs to deliver an overall performance of 720 petaflops of training, 1.4 exaflops of inference."

NVIDIA's Blackwell AI chip faces delays due to server overheating issues, affecting major tech firms' plans for its release.

According to insiders familiar with the situation who spoke with The Information, Nvidia's Blackwell GPUs for AI and HPC overheat when used in servers with 72 processors inside. T

Nvidia's upcoming Blackwell GPUs, already delayed to market, are reportedly facing severe overheating issues in high-capacity server racks, raising concerns over deployment timelines.

Nvidia’s newest artificial intelligence systems may or may not have an overheating issue. But such is the AI market that the chipmaker and its suppliers are unlikely to have any problem filling the

The server rack Nvidia designed for Blackwell —which can connect up to 72 GPUs at a time—is reportedly causing the overheating issue. Nvidia has repeatedly redesigned the racks, which could result in GPU server shipments being delayed and new Google, Microsoft, or Meta data centers may not be able to open on schedule.

Nvidia's next-generation Blackwell processors are facing significant challenges with overheating when installed in high-capacity server racks, reports The Information. These issues have reportedly led to design changes and delays and raised concerns among customers like Google,

Nvidia stock has fallen back slightly from record highs as the market prepares for its third-quarter earnings report.