Serve a Model from an NFS Volume
Connect a model that already exists on NAS or an NFS path as a NuFi Volume, register it in Model Artifacts, and deploy it as a Serving. Use this path when you want to reuse an existing storage location without downloading model files again.
Prerequisites
- An administrator must register an NFS StorageClass. See StorageClass.
- The NFS share path must be the parent directory of the model folder.
1. Create an NFS Volume
In the left sidebar, click Volumes and then Create. Select the NFS StorageClass registered by the administrator and connect the existing path.
| Field | Example |
|---|---|
| Name | tutorial-volume-nfs |
| Storage Class | NFS StorageClass |
| Mount Path | NAS path containing the model folder |
After creation, confirm that the status is Bound and that the model folder is visible in the Files tab.
2. Register the Model
In the left sidebar, click Model Artifacts and run Register Model.
| Field | Example |
|---|---|
| Model Name | qwen-instruct-tutorial-nfs |
| Version | v1 |
| Volume | tutorial-volume-nfs |
| Path | Model folder inside the NFS Volume |
| Format | SafeTensors |
When validation succeeds, register the model version.
3. Choose a Serving Path
For GPU serving, run Quick Deploy from the model detail page.
For NPU serving, compile the source artifact first in Model Compilations. When compilation reaches Succeeded, run Quick Deploy with the generated NPU artifact.
4. Create the Serving
In the Quick Deploy dialog, confirm the model, version, and artifact, then enter a Serving name.
| Field | Example |
|---|---|
| Service Name | nfs-model-serving |
| Version | v1 |
| Artifact | Source artifact for GPU serving, compiled artifact for NPU serving |
The deployment is complete when the Serving status becomes Running.
Next Steps
To check the serving model's response, continue to Test Responses in Playground.
To check device and node metrics, continue to Check Metrics in Monitoring.