NVIDIA develops the H100 graphics processor used for generative-AI computing.
The NVIDIA H100 is a data-center graphics processing unit, or GPU, based on the company’s Hopper architecture. It is designed for demanding workloads such as training and running artificial-intelligence models, scientific computing, and large-scale data analysis.
NVIDIA was founded in 1993 by Jensen Huang, Chris Malachowsky, and Curtis Priem. It first became widely known for GPUs used in computer graphics and video games, but its CUDA software platform helped developers use those processors for general-purpose parallel computing.
That combination of hardware and software positioned NVIDIA at the center of the modern AI infrastructure market. The H100 is not the same product as a consumer GeForce graphics card, although both are built by NVIDIA and use related GPU technology.