Chapter 4. Developer Preview features
This section describes Developer Preview features in Red Hat OpenShift AI 2-latest. Developer Preview features are not supported by Red Hat in any way and are not functionally complete or production-ready. Do not use Developer Preview features for production or business-critical workloads. Developer Preview features provide early access to functionality in advance of possible inclusion in a Red Hat product offering. Customers can use these features to test functionality and provide feedback during the development process. Developer Preview features might not have any documentation, are subject to change or removal at any time, and have received limited testing. Red Hat might provide ways to submit feedback on Developer Preview features without an associated SLA.
For more information about the support scope of Red Hat Developer Preview features, see Developer Preview Support Scope.
- Support for AppWrapper in Kueue
- AppWrapper support in Kueue is available as a Developer Preview feature. The experimental API enables the use of AppWrapper-based workloads with the distributed workloads feature.
- Distributed InstructLab training
InstructLab is an open-source project for enhancing large language models (LLMs) in generative artificial intelligence (gen AI) applications. It fine-tunes models using synthetic data generation (SDG) techniques and a structured taxonomy to create diverse, high-quality training datasets.
There are two ways to run the InstructLab training flow: the InstructLab pipeline, which is the recommended approach, and the standalone script:
InstructLab pipeline
The InstructLab pipeline is now available as a Developer Preview feature, enabling you to run the full InstructLab workflow through a data science pipeline in OpenShift AI. For prerequisites and setup instructions to run this pipeline, see Running InstructLab Pipeline with Data Science Pipelines on RHOAI.
ImportantYou must have NVIDIA GPU Operator 24.6 installed to use the InstructLab pipeline in OpenShift AI 2.17.
Standalone script
Distributed InstructLab training is available as a Developer Preview feature, offering enhanced performance for training tasks in distributed environments compared to single-node setups. By orchestrating multi-node training jobs, this feature improves efficiency and scalability and allows users to leverage distributed resources for more effective AI model development. To implement the full InstructLab training flow with the standalone script, including data preparation, transfer, and distributed execution, see Distributed InstructLab Training on RHOAI.