Hpe Proliant Server Dl380a Gen11 2U Dual Processor Nvme Ai Inference

Hpe Proliant Server Dl380a Gen11 2U Dual Processor Nvme Ai Inference

Product Description

The HPE ProLiant DL380a Gen11 is a 2U dual‑socket GPU‑optimized server purpose‑built for AI inference, deep learning training, and HPC. Powered by 4th/5th Gen Intel Xeon Scalable processors (up to 64 cores per CPU, 350W TDP) and 24 DDR5 DIMM slots (up to 3TB at 5600 MT/s), it features dedicated GPU zones supporting up to 4 double‑width (600W) or 8 single‑width GPUs with NVLink. With 8 front NVMe/EDSFF bays (PCIe 5.0), dual M.2 RAID1 boot drives, and iLO6 management, the DL380a Gen11 delivers accelerated compute and ultra‑fast storage for AI clusters.

Key Differentiators

• Dual 4th/5th Gen Intel Xeon Scalable (up to 64 cores/CPU, 350W TDP)

• 24 x DDR5 DIMM slots — up to 3TB at 5600 MT/s (ECC, mirroring, hot spare)

• 8 x front NVMe/EDSFF bays (PCIe 5.0) — no traditional SAS/SATA

• Dual M.2 NVMe (RAID1, hot‑swap) for system boot

• Up to 4 double‑width (600W) or 8 single‑width GPUs with NVLink support

• 4 x PCIe 5.0 + 2 x OCP 3.0 x16 expansion slots

• Standard SR932i-p / SR416i-o PCIe 5.0 RAID (RAID 0/1/10)

• 1+1 or 2+2 redundant hot‑swap PSUs (up to 4 x 2200W Titanium)

• 6 dual‑rotor hot‑swap fans with dedicated GPU cooling zone

• Standard OCP 3.0 4 x 1GbE; optional 10/25/100GbE

• iLO6 Standard with remote monitoring, deployment, and OneView

• TPM 2.0, chassis intrusion detection, silicon root of trust

Specifications