The HPE ProLiant DL380a Gen11 server is a GPU server built for the growing demands of enterprise AI, with the support for 4 double-wide or 8 single-wide accelerators in a standard 2U 2P form factor. The "a" stands for accelerator optimized, which provides excellent cooling performance for dense GPUs. Powered by 4th and 5th Generation Intel® Xeon® Scalable Processors and cuttingedge GPUs, the HPE ProLiant DL380a Gen11 server can accelerate machine learning, deep learning, AI training and inference workloads, as well as advanced engineering applications or graphic intensive workloads.