A powerhouse acceleration server purpose built to tackle the most complex AI and HPC workloads.
Quick Deployment with Great Serviceability
The architecture is designed around a toolless modular philosophy. Major components can be removed from the system chassis without unmounting from the rack for better serviceability and increased system uptime.
The modularityin this innovative design allows for forward support of next generation CPUs and GPUs.
This server is optimized to accelerate training for massive data sets, huge AI models such as natural language processing, large language models, and supercomputing applications.
⦿ 2x Top Bin Intel® Xeon® Sapphire Rapids processors
⦿ 18x SFF All-NVMe drive bays for GPUDirect storage and boot drive
⦿ 10x OCP NIC 3.0 TSFF for GPUDirect RDMA
⦿ 8x Hopper H100 SXM5 GPU modules with HGX baseboard
⦿ Tool-less, hot-swap designs for drive trays and fan modules
⦿ Easy service with OCP3.0 pull-tab & ejector without opening chassis