Mount storage in endpoints
Endpoints can mount PersistentVolumeClaims to serve models or data directly from persistent storage, instead of pulling from a container registry on every pod restart. This is useful for large model files that are expensive to download.
Mount a PVC into an endpoint pod to serve models or data from persistent storage.
Mount storage during endpoint creation
Navigate to Endpoints
Navigate to Workbench > Endpoints and click Deploy Endpoint.
Configure the endpoint
Configure the model, runtime, and sizing as usual.
Add a volume
In the Storage section of the creation wizard, click Add Volume.
Select the PVC
Select the PVC containing your model files.
Set the mount path
Set the Mount path (for example, /models).
Configure the model path
In the runtime configuration, point the model path to the mount location:
MODEL_PATH=/models/my-model.pt
Success looks like this: the endpoint is created with the storage mounted, and users can access files through the endpoint interface.
Deploy the endpoint
Complete the rest of the form and click Deploy.
The endpoint pods mount the PVC at startup. Scaling replicas share the same PVC (requires ReadOnlyMany or ReadWriteMany access mode).
Access mode considerations
| Access mode | Works with endpoints? | Notes |
|---|---|---|
| ReadWriteOnce | Single replica only | Pod is locked to one node |
| ReadOnlyMany | Yes (recommended) | Multiple replicas, read-only access |
| ReadWriteMany | Yes | Multiple replicas, read-write access |
For serving, ReadOnlyMany is usually sufficient and avoids write contention.
If your storage class does not support ReadOnlyMany, consider using an NFS-backed PVC which supports multi-reader access by default.