Nvidia CEO Jensen Huang announced the development of the DGX GH200 supercomputer at the Computex expo in Taiwan. The supercomputer is designed to assist companies in creating generative AI models, which is a growing trend in the industry. The DGX GH200 is expected to be completed by the end of the year and features an NVLink Switch System that allows 256 GH200 Grace Hopper Superhips to work together as a single graphics processing unit, delivering 1 exaflop performance and 144 terabytes of shared memory. The DGX GH200 has caught the attention of major tech companies like Meta, Microsoft, and Google Cloud, who are expected to be early adopters of the solution.