Generative AI (GenAI) stands out as this decade’s most promising innovation accelerator, with 78% of IT decision-makers expressing considerable excitement about its potential impact on their organizations. Most view GenAI as a tool for achieving productivity gains, process streamlining, and cost savings, making its adoption critical for organizations aiming to compete effectively in the new digital era.
Dell and AMD have collaborated to expand the Dell Generative AI Solutions portfolio, emphasizing the importance of open ecosystems and silicon diversity in providing customers with simple, trusted, and tailored AI solutions. This collaboration addresses the growing challenges in today’s AI landscape, where the surge in data raises crucial questions about how to harness its innovation potential.
The Dell PowerEdge XE9680, the fastest ramping solution in Dell’s history, will support the upcoming AMD Instinct MI300X accelerator, offering businesses increased choice in AI performance. With eight MI300X GPUs, 192GB of 5.3 TB/s High Bandwidth Memory (HBM3) per GPU, and over 21 petaflops of FP16 performance, the PowerEdge XE9680 with MI300X democratizes access to GenAI. It allows enterprises to train larger models, reduce data center footprints, lower TCO, and gain a competitive edge.
In addition to the AMD MI300X Instinct Accelerator support, Dell is introducing the next phase of Dell Generative AI Solutions.
The Dell Validated Design for Generative AI, powered by AMD ROCm-supported AI frameworks and set to launch next year, streamlines the deployment of reliable Generative AI (GenAI). This design encompasses open-source Large Language Models (LLMs), leveraging AMD ROCm’s open-source drivers, development toolkits, and APIs for AMD Instinct accelerators.
Dell Validated Designs provides Dell customers with an uncomplicated approach to constructing dependable GenAI platforms customized to their requirements, eliminating the challenges associated with integration, performance, and sizing considerations.
Dell’s latest eBook and infographic showcase how ROCm-optimized open-source AI and ML frameworks, such as PyTorch, TensorFlow, ONNX-RT, JAX, and Triton, natively support the PowerEdge XE9680 with MI300X, enabling seamless drop-in support for LLMs based on these popular frameworks.
By: Dave Lincoln, Vice President, Compute Systems, Dell Technologies