GPU-related Errors when installing Red Hat OpenShift AI Addon on Red Hat OpenShift Container Platform in IBM Cloud

[Saikiran9824-pronteff]

Important Note: NVIDIA AI Enterprise customers can get support from NVIDIA Enterprise support. Please open a case here.

Describe the bug
I want to configure RedHat OpenShift AI on IBM Cloud for that I were trying to install OpenShift AI and their pre-requisites( OpenShift Pipelines, Node Feature Discovery, NVIDIA GPU Operator) Operator's but getting NVIDIA operator error after installing.
Error logs:
oc logs gpu-feature-discovery-p2jfj -c toolkit-validation | tail -n 1
2025-09-05T03:46:38.612205612Z waiting for nvidia container stack to be setup

[Saikiran9824-pronteff]

Shared Must Gather logs to operator_feedback@nvidia.com

[tariq1890]

From the must-gather artifacts shared, It seems like you're using OpenShift 4.18.22. There is a known issue in OpenShift versions 4.18.22 and 4.18.23 which causes GPU Operator deployments to fail. Please upgrade to Openshift 4.18.24 or greater to fix this issue

See here for more details

[karthikvetrivel]

Hey! As mentioned above, please upgrade to Openshift 4.18.24 or greater to fix this issue. I am going to close this issue as there has been no activity on this issue since. If this issue is still relevant with the latest version of the NVIDIA GPU Operator, please feel free to reopen it or open a new one with updated details.