Hosted on MSN2mon
Nvidia's MLPerf submission shows B200 offers up to 2.2x training performance of H100
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.
NVIDIA CEO Jensen Huang unveils multi-million supercomputer with 1,528 H100 AI GPUs in Denmark — six months after development began to unlock "the era of com…
For context, the supercomputer is based on NVIDIA's DGX SuperPOD AI data center infrastructure platform and leverages the ...
CRN1y
Nvidia: Equinix Private AI Service Will Help Partners Close DGX System Deals ‘Faster’
“All DGX SuperPOD customers get the same lead time ... Long lead times for systems containing Nvidia’s H100 GPUs, including DGX, have been a common complaint of OEMs and channel partners ...