Chapter 5. Integration with Red Hat OpenShift AI
You can use Red Hat OpenShift AI and Red Hat AI Model Optimization Toolkit to experiment with model training, fine-tuning, and compression. The OpenShift AI integration of Red Hat AI Model Optimization Toolkit provides two introductory examples:
- A workbench image and notebook that demonstrates the compression of a tiny model, that you can run on CPU, highlighting how calibrated compression can improve over data-free approaches.
- A data science pipeline that extends the same workflow to a larger Llama 3.2 model, highlighting how users can build automated, GPU-accelerated experiments that can be shared with other stakeholders from a single URL.
Both are available in the Red Hat AI Examples repository.
The OpenShift AI integration of Red Hat AI Model Optimization Toolkit is a Developer Preview feature.