

HPE ProLiant Compute DL384 Gen12 with NVIDIA GH200 NVL2 - Next-level performance for enterprise AI

Next-gen AI: Transforming enterprises.




HPE ProLiant Compute DL384 Gen12
Does your enterprise need a server to dramatically enhance performance for AI inferencing workloads in the era of accelerated computing and generative AI with the modern NVIDIA GH200 Grace Hopper™ Superchip?
The HPE ProLiant Compute DL384 Gen12 provides outstanding coherent memory and memory bandwidth with up to two superchips per server with NVIDIA GH200 NVL2, allowing teams to run larger models faster and more cost-effectively. By partnering with NVIDIA, Hewlett Packard Enterprise continues to innovate with impressive infrastructure enhancements to help customers unlock scaled-out and accelerated computing for generative AI. With superchip performance in your AI factory, HPE ProLiant Compute DL384 Gen12 delivers superb performance per GPU in the HPE ProLiant portfolio. Simplify your approach to scaling with data demands and integrate accelerated compute to reliably prepare your data center for mixed workloads and retrieval-augmented generation (RAG) in the modern hybrid reality.
Contact Us
Chat with usMaximize your HPE ProLiant Compute DL384 Gen12
What's New
- The first HPE ProLiant rack mount server with the NVIDIA GH200 Grace Hopper™ Superchip.
- Support for dual NVIDIA GH200 Grace Hopper Superchips with NVIDIA GH200 NVL2.
- The GH200 NVL2 fuses two Grace CPUs and two Hopper GPUs in an innovative architecture to deliver 8 petaflops of AI performance into a single node.
- The GH200 NVL2 offers up to 3.5X more GPU memory capacity and 3X more bandwidth than the NVIDIA H100 Tensor Core GPU in a single server for compute- and memory-intensive workloads.1
- Train, tune, and deploy generative AI models with confidence.
The HPE ProLiant Compute DL384 Gen12 features NVIDIA GH200 NVL2 Grace Hopper Superchips servers that dramatically increase memory space and bandwidth when compared to a single superchip server.
Show More {"title":"Modernize Your Infrastructure for the Future of AI","keyList":["The HPE ProLiant Compute DL384 Gen12 features NVIDIA GH200 NVL2 Grace Hopper Superchips servers that dramatically increase memory space and bandwidth when compared to a single superchip server.","With up to with 1.2 TB of combined fast memory, a high-bandwidth connection between the NVIDIA Grace CPU and Hopper GPU can help scientists and researchers uncover unprecedented solutions to complex problems by easily handling larger LLMs and supporting applications that run terabytes of data.","Achieve greater performance per dollar invested on inference by connecting two GH200 superchips with NVLink™ in a single node to boost innovation, increase resource utilization, leverage data to enhance efficiency, and improve ROI.","Innovative architecture allows lower latency of responses and enables computationally-demanding workloads to easily run on fewer nodes, reducing the costs associated with maintaining complex distributed architectures and multiple operating systems."]}
Arm is a registered trademark of Arm Limited. Ubuntu is a registered trademark of Canonical Ltd. NVLink and NVIDIA are trademarks and/or registered trademarks of NVIDIA Corporation in the U.S. and other countries. All third-party marks are property of their respective owners.
1 Visit URL https://www.nvidia.com/en-us/data-center/grace-hopper-superchip