Chapter 6. Working with hardware profiles

Procedure

1. From the OpenShift AI dashboard, click Settings Hardware profiles.

   The Hardware profiles page appears, displaying existing hardware profiles. To enable or disable an existing hardware profile, on the row containing the relevant hardware profile, click the toggle in the Enabled column.

2. Click Create hardware profile.

   The Create hardware profile page appears.

3. In the Name field, enter a name for the hardware profile.
4. Optional: To change the default name of your Kubernetes resource, click Edit resource name and enter a name in the Resource name field. The resource name cannot be edited after creation.
5. Optional: In the Description field, enter a description for the hardware profile.

6. In the Visiblity section, set the hardware profile visibility level:

   1. To access the hardware profile in all areas of OpenShift AI, leave the Visible everywhere radio button selected.
   2. Click the Limited visibility radio button to limit the areas of OpenShift AI where your data scientists can use the hardware profile.

7. Optional: Configure node resource request limits:

   1. Click Add resource.

      The Add resource dialog opens.

   2. In the Resource label field, enter a unique resource label.
   3. In the Resource identifier field, enter a unique resource identifier.
   4. From the Resource type field, select a resource type from the list.
   5. In the Default field, enter the default resource request limit. This value must be equal to or between the minimum and maximum limits.
   6. In the Minimum allowed field, enter the minimum number of resources that users can request.

   7. In the Maximum allowed field, enter the maximum number of resources that users can request:

      1. To set a specific maximum request limit, click the Set maximum limit radio button and enter a value.
      2. To set no maximum request limit, click the No maximum limit radio button.
   8. Click Add.

8. Optional: Add a node selector to schedule pods on nodes with matching labels.

   1. Click Add node selector.

      The Add node selector dialog opens.

   2. In the Key field, enter a node selection key. The key must begin with a letter or number, and may contain letters, numbers, hyphens, dots, and underscores.
   3. In the Value field, enter a node selection value. The value must begin with a letter or number, and may contain letters, numbers, hyphens, dots, and underscores.
   4. Click Add.

9. Optional: Add a toleration to schedule pods with matching taints.

   1. Click Add toleration.

      The Add toleration dialog opens.

   2. From the Operator list, select one of the following options:

      • Equal - The key/value/effect parameters must match. This is the default.
      • Exists - The key/effect parameters must match. You must leave a blank value parameter, which matches any.

   3. From the Effect list, select one of the following options:

      • None
      • NoSchedule - New pods that do not match the taint are not scheduled onto that node. Existing pods on the node remain.
      • PreferNoSchedule - New pods that do not match the taint might be scheduled onto that node, but the scheduler tries not to. Existing pods on the node remain.
      • NoExecute - New pods that do not match the taint cannot be scheduled onto that node. Existing pods on the node that do not have a matching toleration are removed.
   4. In the Key field, enter a toleration key. The key must begin with a letter or number, and may contain letters, numbers, hyphens, dots, and underscores.
   5. In the Value field, enter a toleration value. The value must begin with a letter or number, and may contain letters, numbers, hyphens, dots, and underscores.

   6. In the Toleration Seconds section, select one of the following options to specify how long a pod stays bound to a node that has a node condition:

      • Forever - Pods stays permanently bound to a node.
      • Custom value - Enter a value, in seconds, to define how long pods stay bound to a node that has a node condition.
   7. Click Add.
10. Click Create hardware profile.

Procedure

1. From the OpenShift AI dashboard, click Settings Hardware profiles.

   The Hardware profiles page appears. Existing hardware profiles are displayed. To enable or disable a hardware profile, on the row containing the relevant hardware profile, click the toggle in the Enabled column.

2. Click the action menu (⋮) and select Edit from the list.

   The Edit hardware profile dialog opens.

3. Make your changes.
4. Click Update hardware profile.

Procedure

1. From the OpenShift AI dashboard, click Settings Hardware profiles.

   The Hardware profiles page appears, displaying existing hardware profiles.

2. Click the action menu (⋮) beside the hardware profile that you want to delete and click Delete.

   The Delete hardware profile dialog opens.

3. Enter the name of the hardware profile in the text field to confirm that you intend to delete it.
4. Click Delete.

Procedure

1. From the OpenShift AI dashboard, click Settings Workbench images.

   The Workbench images page appears. Previously imported workbench images are displayed.

2. Click the action menu (⋮) and select Edit from the list.

   The Update workbench image dialog opens.

3. From the Accelerator identifier list, select an identifier to set its accelerator as recommended with the workbench image. If the workbench image contains only one accelerator identifier, the identifier name displays by default.

4. Click Update.

   Note

   If you have already configured an accelerator identifier for a workbench image, you can specify a recommended accelerator for the workbench image by creating an associated hardware profile. To do this, click Create profile on the row containing the workbench image and complete the relevant fields. If the workbench image does not contain an accelerator identifier, you must manually configure one before creating an associated hardware profile.

Procedure

1. From the OpenShift AI dashboard, click Settings Serving runtimes.

   The Serving runtimes page opens and shows the model-serving runtimes that are already installed and enabled in your OpenShift AI deployment. By default, the OpenVINO Model Server runtime is pre-installed and enabled in OpenShift AI.

2. Edit your custom runtime that you want to add the recommended accelerator tag to, click the action menu (⋮) and select Edit.

   A page with an embedded YAML editor opens.

   Note

   You cannot directly edit the OpenVINO Model Server runtime that is included in OpenShift AI by default. However, you can clone this runtime and edit the cloned version. You can then add the edited clone as a new, custom runtime. To do this, click the action menu beside the OpenVINO Model Server and select Duplicate.

3. In the editor, enter the YAML code to apply the annotation opendatahub.io/recommended-accelerators. The excerpt in this example shows the annotation to set a recommended tag for an NVIDIA GPU accelerator:

   metadata:
   	annotations:
   		opendatahub.io/recommended-accelerators: '["nvidia.com/gpu"]'

   Copy to Clipboard
4. Click Update.