Dell has expanded its high-performance computing portfolio for AI workloads by adding an AMD-powered server, specifically designed to support large language models (LLMs). This new addition complements
Dell’s existing Nvidia-powered options, offering customers more variety in their AI infrastructure choices.The latest server has 8 AMD M1300X acceleratorsThe latest server, the Dell PowerEdge XE9680, is equipped with eight AMD Instinct MI300X accelerators. These accelerators are notable for their 1.5GB of high-bandwidth memory (HBM3) and their impressive performance capacity, exceeding 21 petaFLOPS. This makes them particularly suitable for businesses looking to train and operate their own in-house LLMs.
DellOne of the key features of the new Dell offering is its scalability. Customers can scale the systems they deploy using the global memory interconnect (xGMI) standard. Additionally, AMD’s GPUs can be connected over an Ethernet-based AI fabric with a Dell PowerSwitch Z9664F -ON. This release follows Dell’s earlier launch of a unit fitted with Nvidia H100 GPUs.Another significant aspect of Dell’s strategy is the introduction of a new standard called Dell Validated Design for Generative AI with AMD.
This standard provides a framework for organizations to run their own hardware and networking architecture for LLMs. It emphasizes the use of AMD ROCm powered AI frameworks, an open-source package including drivers, development toolkits, and APIs compatible with AMD Instinct accelerators.
These frameworks support popular AI software like PyTorch, TensorFlow, and OpenAI Triton, all of which have native support on the PowerEdge XE9680 fitted with AMD accelerators .Dell’s commitment to standards-based networking, as demonstrated by its membership in the Ultra Ethernet Consortium (UEC), signifies a departure from Nvidia’s approach. Unlike Nvidia, AMD and Dell advocate for an open Ethernet for AI, enabling interoperability of switches from different vendors within the same system.
Dell’s approach encourages businesses to adopt an open strategy encompassing computing, fabric, and storage components essential for powering in-house generative AI models.The new hardware and services that constitute Dell’s latest push in AI are expected to be available in the first half of the next year. This development is part of Dell’s broader effort to provide versatile and powerful solutions for businesses engaging in generative AI and other advanced computing tasks.