HPE ProLiant Compute AI Solutions

The HPE ProLiant DL380a Gen12 is an ultra-scalable 4U platform purpose-built for enterprise AI inferencing, fine-tuning, and hybrid workloads. Featuring dual Intel® Xeon® 6 processors and support for up to eight NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs or NVIDIA H200 NVL GPUs, it delivers breakthrough acceleration for generative AI, agentic AI, and physical AI workloads. With NVLink connectivity, advanced cooling options (air or direct liquid), and HPE iLO 7 Silicon Root of Trust, this server combines massive GPU density, enterprise-grade security, and cloud-native management to power AI factories, multimodal inference, and high-performance visualization at scale.

The HPE ProLiant DL384 Gen12 is engineered for enterprise-scale AI, delivering exceptional performance for large language model fine-tuning, inference, and Retrieval-Augmented Generation (RAG). Powered by dual NVIDIA GH200 Grace Hopper Superchips with up to 1.2 TB of unified, coherent memory and 5 TB/s bandwidth, it offers 2x higher inference performance compared to previous generations, making it ideal for memory-intensive and mixed AI workloads. The DL384 Gen12 enables organizations to accelerate generative AI adoption while maintaining enterprise-grade security and operational efficiency.

The HPE ProLiant DL385 Gen11 is an AI-optimized 2U server designed to power agentic and physical AI workloads such as robotics, digital twins, and real-time simulation. Featuring AMD EPYC™ processors and up to two NVIDIA RTX PRO 6000 Blackwell GPUs, it delivers exceptional compute and GPU acceleration for AI reasoning, generative design, and immersive visualization. With enterprise-grade security, cloud-native management, and integration with NVIDIA AI Enterprise and Blueprints, the DL385 Gen11 enables organizations to deploy and scale advanced AI applications efficiently and securely.

The HPE ProLiant DL145 Gen11 is purpose-built for edge environments, delivering real-time insights and AI inferencing where data is generated. Powered by 4th Gen AMD EPYC™ processors and supporting up to three NVIDIA GPUs, it combines high performance with a compact, rugged design that thrives in harsh conditions—operating from -5°C to 55°C, with dust filtration and vibration tolerance. Its quiet acoustics, fast deployment via HPE Compute Ops Management, and enterprise-grade security make it ideal for AI-driven video analytics, industrial automation, and retail intelligence. This platform enables organizations to reduce latency, cut bandwidth costs, and unlock AI at the edge for smarter, faster decision-making.