The Dell Validated Design for Generative AI Inferencing with NVIDIA has been developed to address the needs of enterprises that need to develop and run custom AI LLMs using domain-specific data that is relevant to their own organization.
Dell Technologies and NVIDIA have designed a scalable, modular, and high-performance architecture that enables enterprises to more quickly design and deploy an inferencing solution that has been validated and performance-tested to accelerate the time to value and to reduce the risk and uncertainty by using a proven design.
This guide provides design guidance and a fully validated reference architecture for generative AI inferencing. Topics that were discussed include:
While this design focuses on AI inferencing of pretrained models, it is the first in a series of validated designs for generative AI that focus on all facets of the generative AI life cycle, including inferencing, model customization, and model training. While these designs focus on generative AI use cases, the architecture is more broadly applicable to more general AI use cases as well.
With this project, Dell Technologies and NVIDIA enable organizations to deliver full-stack generative AI solutions built on the best of Dell infrastructure and software, combined with the latest NVIDIA accelerators, AI software, and AI expertise. This combination of components enables enterprises to use purpose-built generative AI on-premises to solve their business challenges. Together, we are leading the way in driving the next wave of innovation in the enterprise AI landscape.