mirror of
https://github.com/openshift/openshift-docs.git
synced 2026-02-05 12:46:18 +01:00
82 lines
2.6 KiB
Plaintext
82 lines
2.6 KiB
Plaintext
// Module included in the following assemblies:
|
|
//
|
|
// * microshift_ai/microshift-rhoai.adoc
|
|
|
|
:_mod-docs-content-type: PROCEDURE
|
|
[id="microshift-rhoai-install_{context}"]
|
|
= Installing the {rhoai-full} RPM
|
|
|
|
[role="_abstract"]
|
|
To use AI models in {microshift-short} deployments, install the {rhoai-full} ({rhoai}) RPM with a new {microshift-short} installation. You can also install the RPM on an existing {microshift-short} instance if you restart the system.
|
|
|
|
[NOTE]
|
|
====
|
|
The `microshift-ai-model-serving` RPM contains manifests that deploy `kserve`, with the raw deployment mode enabled, and `ServingRuntimes` objects in the `redhat-ods-applications` namespace.
|
|
====
|
|
|
|
:FeatureName: {rhoai-full}
|
|
include::snippets/technology-preview.adoc[leveloffset=+1]
|
|
|
|
.Prerequisites
|
|
|
|
* The system requirements for installing {microshift-short} have been met.
|
|
* You have root user access to your machine.
|
|
* The {oc-first} is installed.
|
|
* You configured your LVM VG with the capacity needed for the PVs of your workload.
|
|
* You have the RAM and disk space required for your AI model.
|
|
* You configured the required accelerators, hardware, operating system, and {microshift-short} to provide the resources your model needs.
|
|
* Your AI model is ready to use.
|
|
|
|
.Procedure
|
|
|
|
. Install the {microshift-short} AI-model-serving RPM package by running the following command:
|
|
+
|
|
[source,terminal]
|
|
----
|
|
$ sudo dnf install microshift-ai-model-serving
|
|
----
|
|
|
|
. As a root user, restart the {microshift-short} service by entering the following command:
|
|
+
|
|
[source,terminal]
|
|
----
|
|
$ sudo systemctl restart microshift
|
|
----
|
|
|
|
. Optional: Install the release information package by running the following command:
|
|
+
|
|
[source,terminal]
|
|
----
|
|
$ sudo dnf install microshift-ai-model-serving-release-info
|
|
----
|
|
+
|
|
[NOTE]
|
|
====
|
|
The `microshift-ai-model-serving-release-info` RPM contains a JSON file with image references useful for offline procedures or deploying a copy of a `ServingRuntime` Custom Resource to your namespace during a bootc image build.
|
|
====
|
|
|
|
.Verification
|
|
|
|
* Verify that the `kserve` pod is running in the `redhat-ods-applications` namespace by entering the following command:
|
|
+
|
|
[source,terminal]
|
|
----
|
|
$ oc get pods -n redhat-ods-applications
|
|
----
|
|
+
|
|
.Example output
|
|
+
|
|
[source,text]
|
|
----
|
|
NAME READY STATUS RESTARTS AGE
|
|
kserve-controller-manager-7fc9fc688-kttmm 1/1 Running 0 1h
|
|
----
|
|
|
|
.Next steps
|
|
|
|
* Create a namespace for your AI model.
|
|
* Package your model into an OCI image.
|
|
* Configure a model-serving runtime.
|
|
* Verify that your model is ready for inferencing.
|
|
* Make requests against the model server.
|