Skip to main content

Mount storage in endpoints

Mount a PVC into an endpoint pod to serve models or data from persistent storage.

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.

TimeAbout 5 minutes
You will needA Kubernetes cluster, a PVC with model data, a registered model
OutcomeAn endpoint serving from persistent storage

Mount storage during endpoint creation

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 modeWorks with endpoints?Notes
ReadWriteOnceSingle replica onlyPod is locked to one node
ReadOnlyManyYes (recommended)Multiple replicas, read-only access
ReadWriteManyYesMultiple 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.

Ask AI
Ask a question about Vantage Compute...