Introduction

The NVIDIA AI Enterprise Software Reference Architecture (RA) provides an example infrastructure stack build that is geared towards OEMs and NVIDIA partners who intend to build systems that are ready for single-tenant production grade AI workloads. While hardware components of the infrastructure stack can be modular, the software components of the infrastructure stack are consistent for various workloads, e.g. Inference, Finetuning, & Retrieval Augmented Generation. There are many different ways to configure and optimize NVIDIA Systems, and this Software Reference Architecture is intended to be software & hardware agnostic while being updated for each NVIDIA AI Enterprise major release. This enables the NVIDIA partner ecosystem to provide additional value and enterprise customers to confidently deliver AI solutions faster, allowing them to focus on running their business rather than fighting deployments. Whether you choose to implement a full-fledged data center using our guidelines or adapt the node configurations with your own networking, the NVIDIA AI Enterprise Software Reference Architecture provides an invaluable starting point. The RA provides full-stack hardware and software recommendations for building high-performance, scalable, secure accelerated computing infrastructure and contains detailed guidance on optimal server, cluster, and network configurations for modern production AI workloads.