This performance brief showcases HPE ProLiant servers achieving multiple #1 rankings across MLPerf™ AI inference benchmarks. Using HPE ProLiant DL384 Gen12 and DL380a Gen11 systems with NVIDIA and Intel accelerators, HPE delivers industry-leading results for image generation, recommendation models, speech recognition, and large language model inference. The results highlight superior performance per GPU, low-latency inference, and scalability for enterprise AI workloads. By combining optimized hardware design with advanced accelerators, HPE demonstrates its leadership in AI infrastructure, enabling organizations to deploy high-performance AI solutions with confidence and efficiency.

Join for free to read