Home > Servers > Specialty Servers > White Papers > Deploy GenAI on the PowerEdge XE9680 with Intel® Gaudi®3 Accelerators > Functional Validation with Optimum Habana
Optimum for Intel® Gaudi®, also known as optimum-habana, is the interface between the Transformers and Diffusers libraries and Intel® Gaudi® AI Accelerators (HPU). It provides a set of tools enabling easy model loading, training, and inference on single- and multi-HPU settings for different downstream tasks. The list of officially validated models and tasks is available here. Users can try any of the thousands of Hugging Face models on Intel® Gaudi® accelerators and tasks with minimal changes.
Note: Optimum Habana goes through periodic releases, so ensure the versions and related configs in the following .yaml files are updated for the latest releases.
Sample configmap.yaml and job.yaml files are provided for Optimum Habana to run a model with FP8 precision. Please refer to the README for additional information on the following GitHub repository:
https://github.com/dell-examples/generative-ai/tree/main/intel-XE9680-gaudi3/optimum-habana
Following are the deployment files in the Optimum Habana repository: