Scales to Tens of Thousands of Grace Blackwell Superchips Using Most Advanced NVIDIA (NVDA) Networking, NVIDIA Full-Stack AI Software, and Storage Features up to 576 Blackwell GPUs Connected as ...

a Top500 supercomputer — DeepL's previous flagship NVIDIA DGX SuperPOD with DGX H100 systems, deployed a year ago in Sweden. The latest deployment will be in the same Swedish data-centre.

Several of Nvidia's partners worldwide are already supplying the DGX H100 system, DGX POD, and DGX SuperPOD. The H100 GPU adopts the Hopper architecture and uses TSMC's 4nm process, while the A100 ...

The WEKApod Data Platform Appliance offers an exceptional, highly performant data management foundation for NVIDIA DGX SuperPOD deployments – a single cluster can deliver up to 18,300,000 IOPs.

The supercomputer will feature 191 DGX H100 systems with a total of 1,528 Nvidia H100 Tensor Core GPUs and 382 Intel Xeon Platinum CPUs connected by Quantum 2 InfiniBand. It will be hosted out of a ...

The DGX B200 systems – used in Nvidia's Nyx supercomputer – boast about 2.27x higher peak floating point performance across FP8, FP16, BF16, and TF32 precisions than last gen's H100 systems.

During Tuesday's Nvidia GTX keynote, CEO Jensen Huang unveiled two so-called "personal AI supercomputers" called DGX Spark and DGX Station, both powered by the Grace Blackwell platform.

A powerful new data platform appliance certified for NVIDIA DGX SuperPOD with NVIDIA DGX H100 systems. The appliance integrates WEKA's AI-native data platform software with class-leading storage ...