The full production of NVIDIA Grace Hopper superchips, which are intended for accelerated generative AI, has commenced.

NVIDIA has announced that the NVIDIA GH200 Grace Hopper Superchip is now in full production and will power systems worldwide to run complex AI and HPC workloads. The GH200-powered systems will join over 400 system configurations powered by different combinations of NVIDIA's latest CPU, GPU, and DPU architectures, including NVIDIA Grace, NVIDIA Hopper, NVIDIA Ada Lovelace, and NVIDIA BlueField. These systems are designed to meet the surging demand for generative AI. NVIDIA founder and CEO Jensen Huang revealed new systems, partners, and additional details surrounding the GH200 Grace Hopper Superchip at COMPUTEX. The chip brings together the Arm-based NVIDIA Grace CPU and Hopper GPU architectures using NVIDIA NVLink-C2C interconnect technology, delivering up to 900 GB/s total bandwidth. This provides incredible compute capability to address the most demanding generative AI and HPC applications. Manufacturers worldwide will soon provide the accelerated infrastructure enterprises need to build and deploy generative AI applications that leverage their unique proprietary data. Systems with GH200 Grace Hopper Superchips are expected to be available beginning later this year.