YouTuber ServeTheHome was granted an inside look at Supermicro's side of the xAI Colossus supercluster. The 100,000 GPU server is operational thanks to simple-to-deploy systems and thousands of ...

Wiwynn is also partnering with ZutaCore to offer a two-phase liquid cooling solution that can offer up to 2.5 kW thermal design power (TDP) and will be demonstrating a two-phase immersion cooling ...

The greatly reduced size of the new M4 Mac mini is fantastic, but will be trouble for colocation services, rack mounters, and ...

Take a look inside of the world's largestr AI supercluster, with Elon Musk's xAI supercomputer powered with 100,000 x NVIDIA H100 AI GPUs.

Not only do massive clusters of GPUs require major amounts of power, but also a cooling system that can handle it all. That's where the xAI Colossus steps in.

HPE, Dell, Lenovo, and Supermicro have all detailed forthcoming servers featuring AMD’s latest data center GPU, the MI325X, and server CPUs, the 5th Generation Epyc family, previously known as Turin.

All products are independently selected by our editors. If you buy something, we may earn an affiliate commission. But there are a lot of options and features to choose between when deciding on ...

SAN JOSE, Calif., Oct. 14, 2024 /PRNewswire/ -- OCP Global Summit -- Flex (NASDAQ: FLEX) today announced new reference platforms for liquid-cooled servers, rack, and power products that will ...

Cisco rolled out a UCS rack server built on the Nvidia HGX platform and introduced plug-and-play infrastructure stacks tailored for specific AI use cases.

The liquid-cooled rack connects 72 NVIDIA Blackwell GPUs and 36 NVIDIA Grace CPUs through fifth-generation NVIDIA NVLink™ and NVLink Switch technologies, enabling powerful AI acceleration in a single ...

The HGX H100 platform is packaged inside Supermicro's 4U Universal GPU Liquid Cooled system, providing easy hot-swappable liquid cooling to each GPU. These servers are loaded inside racks which ...