Ultra-scalable GPU acceleration fo r enterprise AI ideal for fine tuning and inferencing large-scale generative models. The HPE ProLiant Compute DL380a Gen12 is a 4U rack-optimized server designed for AI-intensive workloads, offering robust performance and scalability.

• Processor: Supports 6th Gen Intel® Xeon® Scalable processors with up to 144 cores​.

• Memory: Up to 4 TB DDR5 Smart Memory across 32 DIMM slots​.

• GPU Support: Accommodates up to 8 double-wide GPUs, ideal for AI inference tasks​.

• Storage: Compatible with SFF NVMe and EDSFF drives​.

• Expansion Slots: 6 PCIe Gen5 slots for high-speed connectivity​

• Power Supply: Supports up to 8 M-CRPS power supplies​.

• Management: Integrated HPE iLO Standard with options for Advanced licenses​.

• Security Features: Includes TPM 2.0, optional locking bezel, and intrusion detection