|
1 | 1 | # Using Red Hat OpenShift AI |
2 | 2 |
|
3 | | -[Red Hat OpenShift AI](https://www.redhat.com/en/products/ai/openshift-ai) is a cloud-native AI platform that bundles together many popular model management projects, including [kserve](https://kserve.github.io/website/latest/). |
| 3 | +[Red Hat OpenShift AI](https://www.redhat.com/en/products/ai/openshift-ai) is a cloud-native AI platform that bundles together many popular model management projects, including [KServe](https://kserve.github.io/website/latest/). |
4 | 4 |
|
5 | | -This example shows how to use kserve with RHOAI to deploy a model on OpenShift, using a modelcar image to load the model without requiring any connection to huggingface hub. |
| 5 | +This example shows how to use KServe with RHOAI to deploy a model on OpenShift, using a modelcar image to load the model without requiring any connection to Huggingface Hub. |
6 | 6 |
|
7 | | -## Deploying with kserve |
| 7 | +## Deploying with KServe |
8 | 8 |
|
9 | 9 | !!! note |
10 | | - **Prerequisite**: Ensure that you have a running Kubernetes cluster with RHOAI installed, image pull credentials for `registry.redhat.io/rhelai1`, and Spyre accelerators. |
| 10 | + **Prerequisites**: |
| 11 | + - A running Kubernetes cluster with RHOAI installed |
| 12 | + - Image pull credentials for `registry.redhat.io/rhelai1` |
| 13 | + - Spyre accelerators available in the cluster |
11 | 14 |
|
12 | 15 | <!-- TODO: Link to public docs for cluster setup --> |
13 | 16 |
|
14 | | -1. Create a ServingRuntime to be used for your models |
| 17 | +1. Create a ServingRuntime to serve your models. |
15 | 18 |
|
16 | 19 | ```yaml |
17 | 20 | apiVersion: serving.kserve.io/v1alpha1 |
@@ -49,7 +52,7 @@ This example shows how to use kserve with RHOAI to deploy a model on OpenShift, |
49 | 52 | protocol: TCP |
50 | 53 | ``` |
51 | 54 |
|
52 | | -2. Create an InferenceService for each model you want to deploy. This example demonstrates how to deploy `ibm-granite/granite-3.1-8b-instruct`. |
| 55 | +2. Create an InferenceService for each model you want to deploy. This example demonstrates how to deploy the [Granite](https://www.ibm.com/granite) model `ibm-granite/granite-3.1-8b-instruct`. |
53 | 56 |
|
54 | 57 | ```yaml |
55 | 58 | apiVersion: serving.kserve.io/v1beta1 |
|
0 commit comments