NVIDIA HGX enables advanced AI and HPC workloads in every data center. The platform brings together the full power of NVIDIA GPUs, NVLink, NVIDIA networking, and fully optimized AI and high-performance computing (HPC) software stacks.

2024年11月10日 · At OCP 2024, we managed to grab a few new shots of the NVIDIA HGX B200. While a lot of the focus has been on the GH200 NVL72, GB200 NVL2, and so forth, many of the high-end training systems will still be based on the HGX B200 as the successor to the NVIDIA HGX H100/ H200.

NVIDIA DGX B200 is a fully optimized hardware and software platform that includes the complete NVIDIA AI software stack, including NVIDIA Base Command and NVIDIA AI Enterprise software, a rich ecosystem of third-party support, and access to …

2024年11月2日 · The HGX B200 GPU in particular, seen in our 10U KR9288 server, is a key successor to the NVIDIA HGX H200 8-GPU, which powers our Aivres KR6288. Let’s take a look at some key differences between these two GPUs.

2024年3月18日 · So while NVIDIA’s ridiculously popular H100/H200/GH200 series of accelerators are already the hottest ticket in Silicon Valley, it’s already time to talk about the next generation accelerator...

Supermicro's best-selling AI Training System, the 4U/8U system with NVIDIA HGX H100/H200 8-GPU, will support NVIDIA's upcoming HGX B100 8-GPU. A Supermicro Rack-Level Solution featuring GB200 Superchip systems as server nodes with 2 Grace CPUs and 4 NVIDIA Blackwell GPUs per node.

The NVIDIA HGX B200 revolutionizes data centers with accelerated computing and generative AI powered by NVIDIA Blackwell GPUs. Featuring eight GPUs, it delivers 15X faster trillion-parameter inference with 12X lower costs and energy use, supported by 1.4 TB of GPU memory and 60 TB/s bandwidth.

2024年10月20日 · The NVIDIA Blackwell HGX B200 is built on NVIDIA’s latest Blackwell architecture. It offers an extraordinary 144 petaFLOPs of AI performance, 18 petaFLOPS in FP4 operations, and 192GB of HBM3e memory with 8TB/s bandwidth.

The newer HGX B200 offers a massive boost in performance for AI workloads compared to the HGX H200, particularly in areas like FP8, INT8, FP16/BF16, and TF32 Tensor Core operations, where it boasts a 125% improvement. However, when we look at FP32 and FP64, it’s a smaller leap, at around 18.5%.

As a premier accelerated scaleup x86 platform with up to 15X faster real-time inference performance, 12X lower cost, and 12X less energy use, HGX B200 is designed for the most demanding AI, data analytics, and high-performance computing (HPC) workloads.