Home > AI Solutions > Gen AI > Guides > Design Guide—Generative AI in the Enterprise - Inferencing > Overview
In this chapter, we describe the primary software components used for inferencing, including NVDIA AI Enterprise components such as Triton Inference Server, the NeMo framework for generative AI models, and the NVIDIA Base Command Manager Essentials.
We also explain the Dell PowerEdge servers and NVIDIA GPUs used in the design, including GPU configurations and GPU connectivity, and networking methods.