Chapter 8. Known issues

This section describes known issues in Red Hat OpenShift AI 2-latest and any known methods of working around these issues.

RHOAIENG-15123 (also documented as RHOAIENG-10790 and RHOAIENG-14265) - Pipelines schedule fail after upgrading

When you upgrade to OpenShift AI 2.15, data science pipeline scheduled runs that existed before the upgrade fail to execute. An error message appears in the task pod.

RHOAIENG-15033 - Model registry instances do not restart or update after upgrade from OpenShift AI 2.14 to 2.15

When you upgrade from OpenShift AI 2.14.z to 2.15, existing instances of the model registry component are not updated, which causes the instance pods to use older images than the ones referenced by the operator pod.

From the OpenShift AI dashboard:

Alternatively, from the OpenShift command-line interface (CLI):

RHOAIENG-15008 - Error when creating a bias metric from the CLI without a request name

The user interface might display an error message when viewing bias metrics if the requestName parameter is not set. If you use the user interface to view bias metrics, but want to configure them through the CLI, you must specify a requestName parameter within your payload:

curl -sk -H "Authorization: Bearer ${TOKEN}" -X POST
      --location $TRUSTY_ROUTE/metrics/group/fairness/spd/request
      --header 'Content-Type: application/json'
      --data "{
                 \"modelId\": \"demo-loan-nn-onnx-alpha\",
                 \"protectedAttribute\": \"Is Male-Identifying?\",
                 \"privilegedAttribute\": 1.0,
                 \"unprivilegedAttribute\": 0.0,
                 \"outcomeName\": \"Will Default?\",
                 \"favorableOutcome\": 0,
                 \"batchSize\": 5000,
                 \"requestName\": \"My Request\"

RHOAIENG-14986 - Incorrect package path causes copy_demo_nbs to fail

In OpenShift AI SDK version 0.22.0, the copy_demo_nbs() function of the CodeFlare SDK fails because of an incorrect path to the SDK package. Running this function results in a FileNotFound error.

import codeflare_sdk
import os
import pathlib
import shutil

nb_dir = os.path.join(os.path.dirname(codeflare_sdk.__file__), "demo-notebooks")
def copy_nbs(dir: str = "./demo-notebooks", overwrite: bool = False):
    # does dir exist already?
    if overwrite is False and pathlib.Path(dir).exists():
        raise FileExistsError(
            f"Directory {dir} already exists. Please remove it or provide a different location."
        )

    shutil.copytree(nb_dir, dir, dirs_exist_ok=True)

copy_nbs()

RHOAIENG-14552 - Workbench or notebook OAuth proxy fails with FIPS on OCP 4.16

When using OpenShift 4.16 or newer in a FIPS-enabled cluster, connecting to a running workbench fails because the connection between the internal component oauth-proxy and the OpenShift ingress fails with a TLS handshake error. When opening a workbench, the browser shows an "Application is not available" screen without any additional diagnostics.

RHOAIENG-14271 - Compatibility errors occur when using different Python versions in Ray clusters with Jupyter notebooks

When you use Python version 3.11 in a Jupyter notebook, and then create a Ray cluster, the cluster defaults to a workbench image that contains Ray version 2.35 and Python version 3.9. This mismatch can cause compatibility errors, as the Ray Python client requires a Python version that matches your workbench configuration.

RHOAIENG-14197 - Tooltip text for CPU and Memory graphs is clipped and therefore unreadable

When you hover the cursor over the CPU and Memory graphs in the Top resource-consuming distributed workloads section on the Project metrics tab of the Distributed Workloads Metrics page, the tooltip text is clipped, and therefore unreadable.

RHOAIENG-14095 - The dashboard is temporarily unavailable after the installing OpenShift AI Operator

After you install the OpenShift AI Operator, the OpenShift AI dashboard is unavailable for approximately three minutes. As a result, a Cannot read properties of undefined page might appear.

RHOAIENG-13633 - Cannot set a serving platform for a project without first deploying a model from outside of the model registry

You cannot set a serving platform for a project without first deploying a model from outside of the model registry.

Currently, you cannot deploy a model from a model registry to a project unless the project already has single-model or multi-model serving selected. The only way to select single-model or multi-model serving from the OpenShift AI UI is to first deploy a model or model server from outside the registry.

After you select a serving platform for a project, you can deploy models from a model registry to that project.

RHOAIENG-12516 - fast releases are available in unintended release channels

Due to a known issue with the stream image delivery process, fast releases are currently available on unintended streaming channels, for example, stable, and stable-x.y. For accurate release type, channel, and support lifecycle information, refer to the Life-cycle Dates table on the Red Hat OpenShift AI Self-Managed Life Cycle page.

RHOAIENG-12233 - The chat_template parameter is required when using the /v1/chat/completions endpoint

When configuring the vLLM ServingRuntime for KServe runtime and querying a model using the /v1/chat/completions endpoint, the model fails with the following 400 Bad Request error:

As of transformers v4.44, default chat template is no longer allowed, so you must provide a chat template if the tokenizer does not define one

Transformers v4.44.2 is shipped with vLLM v0.5.5. As of vLLM v0.5.5, you must provide a chat template while querying a model using the /v1/chat/completions endpoint.

RHOAIENG-11024 - Resources entries get wiped out after removing opendatahub.io/managed annotation

Manually removing the opendatahub.io/managed annotation from any component deployment YAML file might cause resource entry values in the file to be erased.

RHOAIENG-8294 - CodeFlare error when upgrading OpenShift AI 2.8 to version 2.10 or later

If you try to upgrade OpenShift AI 2.8 to version 2.10 or later, the following error message is shown for the CodeFlare component, due to a mismatch with the AppWrapper custom resource definition (CRD) version.

ReconcileCompletedWithComponentErrors DataScienceCluster resource reconciled with component errors: 1 error occurred: * CustomResourceDefinition.apiextensions.k8s.io "appwrappers.workload.codeflare.dev" is invalid: status.storedVersions[0]: Invalid value: "v1beta1": must appear in spec.versions

RHOAIENG-7947 - Model serving fails during query in KServe

If you initially install the ModelMesh component and enable the multi-model serving platform, but later install the KServe component and enable the single-model serving platform, inference requests to models deployed on the single-model serving platform might fail. In these cases, inference requests return a 404 - Not Found error and the logs for the odh-model-controller deployment object show a Reconciler error message.

RHOAIENG-7716 - Pipeline condition group status does not update

When you run a pipeline that has condition groups, for example, dsl.lf, the UI displays a Running status for the groups, even after the pipeline execution is complete.

RHOAIENG-6486 - Pod labels, annotations, and tolerations cannot be configured when using the Elyra JupyterLab extension with the TensorFlow 2024.1 notebook image

When using the Elyra JupyterLab extension with the TensorFlow 2024.1 notebook image, you cannot configure pod labels, annotations, or tolerations from an executed pipeline. This is due to a dependency conflict with the kfp and tf2onnx packages.

RHOAIENG-6435 - Distributed workloads resources are not included in Project metrics

When you click Distributed Workloads Metrics > Project metrics and view the Requested resources section, the Requested by all projects value currently excludes the resources for distributed workloads that have not yet been admitted to the queue.

RHOAIENG-6409 - Cannot save parameter errors appear in pipeline logs for successful runs

When you run a pipeline more than once with data science pipelines 2.0, Cannot save parameter errors appear in the pipeline logs for successful pipeline runs. You can safely ignore these errors.

RHOAIENG-12294 (previously documented as RHOAIENG-4812) - Distributed workload metrics exclude GPU metrics

In this release of OpenShift AI, the distributed workload metrics exclude GPU metrics.

RHOAIENG-4570 - Existing Argo Workflows installation conflicts with install or upgrade

Data science pipelines 2.0 contains an installation of Argo Workflows. OpenShift AI does not support direct customer usage of this installation of Argo Workflows. To install or upgrade OpenShift AI with data science pipelines 2.0, ensure that there is no existing installation of Argo Workflows on your cluster. For more information, see Enabling data science pipelines 2.0.

RHOAIENG-3913 - Red Hat OpenShift AI Operator incorrectly shows Degraded condition of False with an error

If you have enabled the KServe component in the DataScienceCluster (DSC) object used by the OpenShift AI Operator, but have not installed the dependent Red Hat OpenShift Service Mesh and Red Hat OpenShift Serverless Operators, the kserveReady condition in the DSC object correctly shows that KServe is not ready. However, the Degraded condition incorrectly shows a value of False.

RHOAIENG-3025 - OVMS expected directory layout conflicts with the KServe StoragePuller layout

When you use the OpenVINO Model Server (OVMS) runtime to deploy a model on the single-model serving platform (which uses KServe), there is a mismatch between the directory layout expected by OVMS and that of the model-pulling logic used by KServe. Specifically, OVMS requires the model files to be in the /<mnt>/models/1/ directory, while KServe places them in the /<mnt>/models/ directory.

KServe pulls model files from the subdirectory in the path that you specified. In this case, KServe correctly pulls model files from the /<s3_storage_bucket>/models/1/ directory in your S3-compatible storage.

RHOAIENG-3018 - OVMS on KServe does not expose the correct endpoint in the dashboard

When you use the OpenVINO Model Server (OVMS) runtime to deploy a model on the single-model serving platform, the URL shown in the Inference endpoint field for the deployed model is not complete.

RHOAIENG-2759 - Model deployment fails when both secured and regular model servers are present in a project

When you create a second model server in a project where one server is using token authentication, and the other server does not use authentication, the deployment of the second model might fail to start.

RHOAIENG-2602 - “Average response time" server metric graph shows multiple lines due to ModelMesh pod restart

The Average response time server metric graph shows multiple lines if the ModelMesh pod is restarted.

RHOAIENG-2585 - UI does not display an error/warning when UWM is not enabled in the cluster

Red Hat OpenShift AI does not correctly warn users if User Workload Monitoring (UWM) is disabled in the cluster. UWM is necessary for the correct functionality of model metrics.

RHOAIENG-2555 - Model framework selector does not reset when changing Serving Runtime in form

When you use the Deploy model dialog to deploy a model on the single-model serving platform, if you select a runtime and a supported framework, but then switch to a different runtime, the existing framework selection is not reset. This means that it is possible to deploy the model with a framework that is not supported for the selected runtime.

RHOAIENG-2468 - Services in the same project as KServe might become inaccessible in OpenShift

If you deploy a non-OpenShift AI service in a data science project that contains models deployed on the single-model serving platform (which uses KServe), the accessibility of the service might be affected by the network configuration of your OpenShift cluster. This is particularly likely if you are using the OVN-Kubernetes network plugin in combination with host network namespaces.

RHOAIENG-2228 - The performance metrics graph changes constantly when the interval is set to 15 seconds

On the Endpoint performance tab of the model metrics screen, if you set the Refresh interval to 15 seconds and the Time range to 1 hour, the graph results change continuously.

RHOAIENG-2183 - Endpoint performance graphs might show incorrect labels

In the Endpoint performance tab of the model metrics screen, the graph tooltip might show incorrect labels.

RHOAIENG-1919 - Model Serving page fails to fetch or report the model route URL soon after its deployment

When deploying a model from the OpenShift AI dashboard, the system displays the following warning message while the Status column of your model indicates success with an OK/green checkmark.

Failed to get endpoint for this deployed model. routes.rout.openshift.io"<model_name>" not found

RHOAIENG-404 - No Components Found page randomly appears instead of Enabled page in OpenShift AI dashboard

A No Components Found page might appear when you access the Red Hat OpenShift AI dashboard.

RHOAIENG-234 - Unable to view .ipynb files in VSCode in Insecured cluster

When you use the code-server notebook image on Google Chrome in an insecure cluster, you cannot view .ipynb files.

RHOAIENG-1128 - Unclear error message displays when attempting to increase the size of a Persistent Volume (PV) that is not connected to a workbench

When attempting to increase the size of a Persistent Volume (PV) that is not connected to a workbench, an unclear error message is displayed.

RHOAIENG-545 - Cannot specify a generic default node runtime image in JupyterLab pipeline editor

When you edit an Elyra pipeline in the JupyterLab IDE pipeline editor, and you click the PIPELINE PROPERTIES tab, and scroll to the Generic Node Defaults section and edit the Runtime Image field, your changes are not saved.

RHOAIENG-497 - Removing DSCI Results In OpenShift Service Mesh CR Being Deleted Without User Notification

If you delete the DSCInitialization resource, the OpenShift Service Mesh CR is also deleted. A warning message is not shown.

RHOAIENG-282 - Workload should not be dispatched if required resources are not available

Sometimes a workload is dispatched even though a single machine instance does not have sufficient resources to provision the RayCluster successfully. The AppWrapper CRD remains in a Running state and related pods are stuck in a Pending state indefinitely.

RHOAIENG-131 - gRPC endpoint not responding properly after the InferenceService reports as Loaded

When numerous InferenceService instances are generated and directed requests, Service Mesh Control Plane (SMCP) becomes unresponsive. The status of the InferenceService instance is Loaded, but the call to the gRPC endpoint returns with errors.

RHOAIENG-130 - Synchronization issue when the model is just launched

When the status of the KServe container is Ready, a request is accepted even though the TGIS container is not ready.

RHOAIENG-3115 - Model cannot be queried for a few seconds after it is shown as ready

Models deployed using the multi-model serving platform might be unresponsive to queries despite appearing as Ready in the dashboard. You might see an “Application is not available" response when querying the model endpoint.

RHOAIENG-1619 (previously documented as DATA-SCIENCE-PIPELINES-165) - Poor error message when S3 bucket is not writable

When you set up a data connection and the S3 bucket is not writable, and you try to upload a pipeline, the error message Failed to store pipelines is not helpful.

RHOAIENG-1207 (previously documented as ODH-DASHBOARD-1758) - Error duplicating OOTB custom serving runtimes several times

If you duplicate a model-serving runtime several times, the duplication fails with the Serving runtime name "<name>" already exists error message.

RHOAIENG-1201 (previously documented as ODH-DASHBOARD-1908) - Cannot create workbench with an empty environment variable

When creating a workbench, if you click Add variable but do not select an environment variable type from the list, you cannot create the workbench. The field is not marked as required, and no error message is shown.

RHOAIENG-432 (previously documented as RHODS-12928) - Using unsupported characters can generate Kubernetes resource names with multiple dashes

When you create a resource and you specify unsupported characters in the name, then each space is replaced with a dash and other unsupported characters are removed, which can result in an invalid resource name.

RHOAIENG-226 (previously documented as RHODS-12432) - Deletion of the notebook-culler ConfigMap causes Permission Denied on dashboard

If you delete the notebook-controller-culler-config ConfigMap in the redhat-ods-applications namespace, you can no longer save changes to the Cluster Settings page on the OpenShift AI dashboard. The save operation fails with an HTTP request has failed error.

RHOAIENG-133 - Existing workbench cannot run Elyra pipeline after notebook restart

If you use the Elyra JupyterLab extension to create and run data science pipelines within JupyterLab, and you configure the pipeline server after you created a workbench and specified a notebook image within the workbench, you cannot execute the pipeline, even after restarting the notebook.

RHOAIENG-11 - Separately installed instance of CodeFlare Operator not supported

In Red Hat OpenShift AI, the CodeFlare Operator is included in the base product and not in a separate Operator. Separately installed instances of the CodeFlare Operator from Red Hat or the community are not supported.

RHODS-12798 - Pods fail with "unable to init seccomp" error

Pods fail with CreateContainerError status or Pending status instead of Running status, because of a known kernel bug that introduced a seccomp memory leak. When you check the events on the namespace where the pod is failing, or run the oc describe pod command, the following error appears:

runc create failed: unable to start container process: unable to init seccomp: error loading seccomp filter into kernel: error loading seccomp filter: errno 524

KUBEFLOW-177 - Bearer token from application not forwarded by OAuth-proxy

You cannot use an application as a custom workbench image if its internal authentication mechanism is based on a bearer token. The OAuth-proxy configuration removes the bearer token from the headers, and the application cannot work properly.

RHOAIENG-5646 (previously documented as NOTEBOOKS-218) - Data science pipelines saved from the Elyra pipeline editor reference an incompatible runtime

When you save a pipeline in the Elyra pipeline editor with the format .pipeline in OpenShift AI version 1.31 or earlier, the pipeline references a runtime that is incompatible with OpenShift AI version 1.32 or later.

As a result, the pipeline fails to run after you upgrade OpenShift AI to version 1.32 or later.

NOTEBOOKS-210 - A notebook fails to export as a PDF file in Jupyter

When you export a notebook as a PDF file in Jupyter, the export process fails with an error.

RHOAIENG-1210 (previously documented as ODH-DASHBOARD-1699) - Workbench does not automatically restart for all configuration changes

When you edit the configuration settings of a workbench, a warning message appears stating that the workbench will restart if you make any changes to its configuration settings. This warning is misleading because in the following cases, the workbench does not automatically restart:

RHOAIENG-1208 (previously documented as ODH-DASHBOARD-1741) - Cannot create a workbench whose name begins with a number

If you try to create a workbench whose name begins with a number, the workbench does not start.

KUBEFLOW-157 - Logging out of JupyterLab does not work if you are already logged out of the OpenShift AI dashboard

If you log out of the OpenShift AI dashboard before you log out of JupyterLab, then logging out of JupyterLab is not successful. For example, if you know the URL for a Jupyter notebook, you are able to open this again in your browser.

RHODS-9789 - Pipeline servers fail to start if they contain a custom database that includes a dash in its database name or username field

When you create a pipeline server that uses a custom database, if the value that you set for the dbname field or username field includes a dash, the pipeline server fails to start.

RHOAIENG-580 (previously documented as RHODS-9412) - Elyra pipeline fails to run if workbench is created by a user with edit permissions

If a user who has been granted edit permissions for a project creates a project workbench, that user sees the following behavior:

RHODS-7718 - User without dashboard permissions is able to continue using their running notebooks and workbenches indefinitely

When a Red Hat OpenShift AI administrator revokes a user’s permissions, the user can continue to use their running notebooks and workbenches indefinitely.

RHOAIENG-1157 (previously documented as RHODS-6955) - An error can occur when trying to edit a workbench

When editing a workbench, an error similar to the following can occur:

Error creating workbench
Operation cannot be fulfilled on notebooks.kubeflow.org "workbench-name": the object has been modified; please apply your changes to the latest version and try again

RHOAIENG-1152 (previously documented as RHODS-6356) - The notebook creation process fails for users who have never logged in to the dashboard

The dashboard’s notebook Administration page displays users belonging to the user group and admin group in OpenShift. However, if an administrator attempts to start a notebook server on behalf of a user who has never logged in to the dashboard, the server creation process fails and displays the following error message:

Request invalid against a username that does not exist.

RHODS-5763 - Incorrect package version displayed during notebook selection

The Start a notebook server page displays an incorrect version number for the Anaconda notebook image.

RHODS-5543 - When using the NVIDIA GPU Operator, more nodes than needed are created by the Node Autoscaler

When a pod cannot be scheduled due to insufficient available resources, the Node Autoscaler creates a new node. There is a delay until the newly created node receives the relevant GPU workload. Consequently, the pod cannot be scheduled and the Node Autoscaler’s continuously creates additional new nodes until one of the nodes is ready to receive the GPU workload. For more information about this issue, see the Red Hat Knowledgebase solution When using the NVIDIA GPU Operator, more nodes than needed are created by the Node Autoscaler.

RHOAIENG-1149 (previously documented RHODS-5216) - The application launcher menu incorrectly displays a link to OpenShift Cluster Manager

Red Hat OpenShift AI incorrectly displays a link to the OpenShift Cluster Manager from the application launcher menu. Clicking this link results in a "Page Not Found" error because the URL is not valid.

RHOAIENG-1137 (previously documented as RHODS-5251) - Notebook server administration page shows users who have lost permission access

If a user who previously started a notebook server in Jupyter loses their permissions to do so (for example, if an OpenShift AI administrator changes the user’s group settings or removes the user from a permitted group), administrators continue to see the user’s notebook servers on the server Administration page. As a consequence, an administrator is able to restart notebook servers that belong to the user whose permissions were revoked.

RHODS-4799 - Tensorboard requires manual steps to view

When a user has TensorFlow or PyTorch notebook images and wants to use TensorBoard to display data, manual steps are necessary to include environment variables in the notebook environment, and to import those variables for use in your code.

RHODS-4718 - The Intel® oneAPI AI Analytics Toolkits quick start references nonexistent sample notebooks

The Intel® oneAPI AI Analytics Toolkits quick start, located on the Resources page on the dashboard, requires the user to load sample notebooks as part of the instruction steps, but refers to notebooks that do not exist in the associated repository.

RHODS-4627 - The CronJob responsible for validating Anaconda Professional Edition’s license is suspended and does not run daily

The CronJob responsible for validating Anaconda Professional Edition’s license is automatically suspended by the OpenShift AI operator. As a result, the CronJob does not run daily as scheduled. In addition, when Anaconda Professional Edition’s license expires, Anaconda Professional Edition is not indicated as disabled on the OpenShift AI dashboard.

RHOAIENG-1141 (previously documented as RHODS-4502) - The NVIDIA GPU Operator tile on the dashboard displays button unnecessarily

GPUs are automatically available in Jupyter after the NVIDIA GPU Operator is installed. The Enable button, located on the NVIDIA GPU Operator tile on the Explore page, is therefore redundant. In addition, clicking the Enable button moves the NVIDIA GPU Operator tile to the Enabled page, even if the Operator is not installed.

RHOAIENG-1135 (previously documented as RHODS-3985) - Dashboard does not display Enabled page content after ISV operator uninstall

After an ISV operator is uninstalled, no content is displayed on the Enabled page on the dashboard. Instead, the following error is displayed:

Error loading components
HTTP request failed

RHODS-3984 - Incorrect package versions displayed during notebook selection

In the OpenShift AI interface, the Start a notebook server page displays incorrect version numbers for the JupyterLab and Notebook packages included in the oneAPI AI Analytics Toolkit notebook image. The page might also show an incorrect value for the Python version used by this image.

RHODS-2956 - Error can occur when creating a notebook instance

When creating a notebook instance in Jupyter, a Directory not found error appears intermittently. This error message can be ignored by clicking Dismiss.

RHOAING-1147 (previously documented as RHODS-2881) - Actions on dashboard not clearly visible

The dashboard actions to revalidate a disabled application license and to remove a disabled application tile are not clearly visible to the user. These actions appear when the user clicks on the application tile’s Disabled label. As a result, the intended workflows might not be clear to the user.

RHOAIENG-1134 (previously documented as RHODS-2879) - License revalidation action appears unnecessarily

The dashboard action to revalidate a disabled application license appears unnecessarily for applications that do not have a license validation or activation system. In addition, when a user attempts to revalidate a license that cannot be revalidated, feedback is not displayed to state why the action cannot be completed.

RHOAIENG-2305 (previously documented as RHODS-2650) - Error can occur during Pachyderm deployment

When creating an instance of the Pachyderm operator, a webhook error appears intermittently, preventing the creation process from starting successfully. The webhook error is indicative that, either the Pachyderm operator failed a health check, causing it to restart, or that the operator process exceeded its container’s allocated memory limit, triggering an Out of Memory (OOM) kill.

RHODS-2096 - IBM Watson Studio not available in OpenShift AI

IBM Watson Studio is not available when OpenShift AI is installed on OpenShift Dedicated 4.9 or higher, because it is not compatible with these versions of OpenShift Dedicated.