Managing Kubernetes Clusters

Configure Accelerators

If your Kubernetes nodes include accelerators, please complete the configuration according to the accelerator type.

NVIDIA GPU

For standard Kubernetes clusters, refer to the Installing the NVIDIA GPU Operator section in the NVIDIA GPU Operator documentation from NVIDIA official documentation to install NVIDIA GPU Operator.

AMD GPU

Please refer to AMD official documentation for the following configuration:

1. The current cluster image supports ROCM software version 6.3.3. Please install the corresponding version of AMDGPU driver. Refer to the AMDGPU driver installation section in the AMD ROCm documentation.

2. The current cluster image supports ROCM software version 6.3.3. Please install the corresponding version of AMD GPU Device Plugin. Refer to the AMD GPU Device Plugin for Kubernetes section in the Device Plugin Documentation.

Create Cluster

1. Log in to the Neutree management interface, click Clusters in the left sidebar, and click Create on the right page.

2. Fill in the configuration information.

   • Basic Information

     Parameter	Description	Editable After Creation
     Name	The name of the cluster.	No
     Workspace	The workspace to which the cluster belongs.	No

   • Image Registry

     Select an image registry for the cluster to store cluster-related container images. If no image registry is available, refer to the Create Container Image Registry section to create one. Not editable after cluster creation.

   • Cluster Type

     The type of cluster, select Kubernetes. Not editable after cluster creation.

   • Provider

     Enter the Kubeconfig string for the cluster, used to access the Kubernetes cluster. Not editable after cluster creation.

   • Routing

     Parameter	Description	Editable After Creation
     Access Mode	Access mode for the routing component: LoadBalancer or NodePort. When selecting LoadBalancer, ensure the Kubernetes cluster supports LoadBalancer services.	Yes
     Replicas	Number of routing component replicas. It’s recommended to set at least 2 for high availability.	Yes
     CPU	CPU allocation for the routing component.	Yes
     Memory	Memory allocation for the routing component.	Yes

   • Model Cache

     Parameter	Description	Editable After Creation
     Name	Model cache name.	No
     Cache Type	Supported cache types: Host Path: Local cache. NFS: NFS cache. PVC: Persistent storage, only supports ReadWriteMany.	Yes
     Cache Path	Path for model cache. For Host Path, specify the host path. For NFS, specify the NFS server path. For PVC, this field is not required.	Yes
     NFS Server Address	IP address or domain name of the NFS server. Only required when cache type is NFS.	Yes
     Storage	Storage capacity for model cache. Only required when cache type is PVC.	Yes
     Storage Class Name	Storage class name for model cache. Only required when cache type is PVC.	No

     If model cache is not configured during creation, it can be added after cluster creation.

3. After confirming the configuration is correct, click Save to complete the creation.

View Cluster

Log in to the Neutree management interface, click Clusters in the left sidebar, and the cluster list on the right will display all current clusters. Click on a cluster name to view details.

On the details page, you can view Basic Information and Monitoring as needed.

Edit Cluster

After cluster creation, you can modify routing and some model cache settings as needed.

1. Log in to the Neutree management interface, click the menu icon on the cluster list or details page, and select Edit.

2. Modify as needed on the configuration page. For parameter descriptions, refer to Create Cluster.

3. After confirming the configuration is correct, click Save to complete the edit.

Delete Cluster

1. Log in to the Neutree management interface, click the menu icon on the cluster list or details page, and select Delete.

2. In the pop-up dialog, confirm and click Delete. The cluster will be permanently deleted.