Lambda Labs has partnered with the server division of Taiwanese electronics company Pegatron to deploy an Nvidia GB200 NVL72 to power its AI compute platform.

In a post on LinkedIn, Pegatron SVR said the rack had arrived at its data center and was “getting ready to be deployed.”

In a separate post on the platform, Lambda engineering and operations manager Vijay Manyam said more details about the deployment would be revealed “soon.”

First revealed in March 2024, Nvidia’s GB200 NVL72 is a liquid cooled server rack featuring 72 GB200 GPUs, 36 Grace CPUs, and nine NVLink switch trays, each of which has two NVLink switches. The company has previously said that this configuration will enable the system to run as a giant GPU, boosting performance.

However, in November 2024, it was reported that the NVL72 racks were overheating, with the chip designer asking its suppliers to make multiple changes to its custom rack design in a bid to solve the issue. It was also reported that the company’s smaller, 36-chip rack has been experiencing similar problems.

It’s believed that the cooling issues have now been addressed, with customers including CoreWeave already having received NVL72 racks. Microsoft was the first cloud provider to deploy Nvidia’s new GB200 GPUs in its AI cloud servers, although according to reports that rack configuration was not a GB200 NVL72.

Founded in 2012, Lambda Labs rents out colocation space in data centers in San Francisco, California, and Allen, Texas, and offers comparatively low-cost GPU-based cloud compute. Alongside the cloud, it provides colocation space and sells GPU desktops.

In July 2024, it was reported that the company was seeking $800m in funding to purchase additional Nvidia GPUs, associated network infrastructure, and software.

The GB200 Superchip has an estimated price of between $60,000 and $70,000, while a GB200 NVL72 rack is thought to cost $3 million.