Tested and verified runtimes for Red Hat OpenShift AI
Tested and verified runtimes let customers use the community versions of model-serving runtimes in OpenShift AI. The Red Hat team tests and verifies new builds of some runtimes against specific versions of OpenShift AI.
Unlike artifacts and binaries for the open-source projects Red Hat supports, not all model-serving runtimes can be built and redistributed. However, to respond to the rapidly changing needs of customers in the AI field, Red Hat tests and verifies new builds of community runtimes in OpenShift AI.
A list of tested and verified runtimes is available at This content is not included.Tested and verified model serving runtimes.
How do I access a tested and verified runtime?
You can access tested and verified runtimes through the upstream community.
Are tested and verified runtimes supported by Red Hat?
No, tested and verified runtimes are not directly supported by Red Hat.
You are responsible for ensuring that you are licensed to use any tested and verified runtimes that you add, and for correctly configuring and maintaining them.
As a customer using a tested and verified runtime on Red Hat OpenShift AI, can I open a support ticket?
Yes, customers can open support tickets. Red Hat can answer questions and help with root cause analysis, workarounds, and so forth. However, Red Hat cannot offer bug fixes or security updates for tested and verified runtimes.
We want to have the same level of support that other Red Hat products offer. What are our options?
Several out-of-the-box runtimes are available in OpenShift AI. Serving your model from one of the standard runtimes provides the same level of support as other Red Hat products.
For more information about using a pre-installed runtime, see This content is not included.Deploying models on the single-model serving platform or This content is not included.Deploying a model by using the multi-model serving platform.
What life cycle can I expect for different versions of tested and verified runtimes?
Red Hat tests the current version of a tested and verified runtime each time there is a new version of OpenShift AI. If a new version of a tested and verified runtime is released in the middle of an OpenShift AI release cycle, it will be tested and verified in an upcoming release.