Managing Dedicated AI Clusters
Dedicated AI clusters are compute resources that you can use to fine-tune custom models or to host endpoints for the pretrained base models and custom models in OCI Generative AI. The clusters are dedicated to your models and not shared with users in other tenancies.
If you have manage permissions for generative-ai-family, you can perform the following tasks for dedicated AI clusters:
- Create a dedicated AI cluster for fine-tuning custom models
- Create a dedicated AI cluster for hosting models
- List the dedicated AI clusters
- Get a dedicated AI cluster's details
- Get a hosting dedicated AI cluster's metrics
- Update a dedicated AI cluster
- Move a dedicated AI cluster
- Delete a dedicated AI cluster
Tip
When you perform the preceding tasks, for the dedicated AI cluster unit size that matches each base model, see Matching Base Models to Clusters. For rules about creating endpoints for the models hosted on clusters, see Adding Endpoints to Hosting Clusters.
When you perform the preceding tasks, for the dedicated AI cluster unit size that matches each base model, see Matching Base Models to Clusters. For rules about creating endpoints for the models hosted on clusters, see Adding Endpoints to Hosting Clusters.