最新消息与更新

Explore the SUPERMICRO AS-5126GS-TNRT2, a 5U dual-processor rack server supporting up to 10 NVIDIA RTX PRO 6000 GPUs. Perfect for AI, deep learning, HPC, and 3D rendering workloads.

As artificial intelligence continues to grow, it is important to measure how efficiently hardware and software can handle real-world AI workloads. The MLPerf Inference 5.1 benchmark provides a standardized way to do this. In recent tests, the Cisco C845A rack server, equipped with eight NVIDIA H200 NVL PCIe GPUs, was used to evaluate the performance of Meta’s Llama2-70B, a large language model with 70 billion parameters.

NVIDIA has introduced the RTX PRO Blackwell series , a new generation of workstation GPUs that deliver supercomputer-level performance in a desktop form factor. The Blackwell architecture is designed for professionals in visualization, simulation, and scientific computing, significantly expanding the power and efficiency of local AI workloads. Supercomputer Performance in a Desktop The flagship RTX PRO 6000 Blackwell GPU supports up to 96GB of GDDR7 memory per card. Workstati