diff --git a/docs/2-Deployment/3-Software/2-wxai.mdx b/docs/2-Deployment/3-Software/2-wxai.mdx index 90f12273..7e81f318 100644 --- a/docs/2-Deployment/3-Software/2-wxai.mdx +++ b/docs/2-Deployment/3-Software/2-wxai.mdx @@ -5,56 +5,109 @@ title: Watsonx ai installation custom_edit_url: null --- -:::note -Associated links with this section -[Installing Multicloud Object Gateway](https://www.ibm.com/docs/en/cloud-paks/cp-data/4.8.x?topic=watsonxai-installing) -::: +## Setup GPU node on OpenShift -## Login to the cluster with cpd-cli +### Install "Node Feature Discovery" -Source the env file +Go to OperatorHub -`source cpd_vars_48.sh` +Search for "Node Feature Discovery" -login with cpd-cli -``` -cpd-cli manage login-to-ocp \ ---username=${OCP_USERNAME} \ ---password=${OCP_PASSWORD} \ ---server=${OCP_URL} -``` +Install + +### Create a NodeFeatureDisocvery CR + +Go to Installed Operators + +Select "Node Feature Discovery" + +Select the box "Provided APIs" + +Select "Create Instance" + +Review the values + +Select "Create" + +### Install "Nvidia GPU Operator" + +Go to OperatorHub + +Search for "Nvidia GPU Operator" + +Install + +### Create "Cluster Policy" + +Go to "Installed Operators" + +Click on "Nvidia GPU Operator" + +Select "ClusterPolicy" tab + +Click "Create ClusterPolicy" -## Installing OLM +Click "Create" -The following services are automatically installed when you install the IBM watsonx.ai service, presuming you haven't installed them already. -- Watson Studio -- Watson Machine Learning -Run the following command to create the required OLM objects for IBM watsonx.ai in the operators project for the instance: +### Reference Links: +:::Note +For additional Information: -```tsx +[OpenShift Docs on Node Feature Discovery](https://docs.openshift.com/container-platform/4.12/hardware_enablement/psap-node-feature-discovery-operator.html#create-nfd-cr-web-console_node-feature-discovery-operator) + +[Nvidia docs on Node Feature Discovery](https://docs.nvidia.com/datacenter/cloud-native/openshift/latest/install-nfd.html#install-nfd) + +[Nvidia docs on Nvidia GPU Operator](https://docs.nvidia.com/datacenter/cloud-native/openshift/latest/install-gpu-ocp.html) +::: + +## Install WatsonX.AI on Cloud Pak for Data + +### Apply the WatsonX.AI OLM: + +To install the WatsonX.AI OLMs: + +``` cpd-cli manage apply-olm \ --release=${VERSION} \ --cpd_operator_ns=${PROJECT_CPD_INST_OPERATORS} \ ---components=watsonx_ai +--components=watsonx_ai \ +--case_download=true \ +--from_oci=true ``` -## Install the CR +### Apply the WatsonX.AI CR: + +To install WatsonX.AI run the following command: -```tsx +``` cpd-cli manage apply-cr \ --components=watsonx_ai \ --release=${VERSION} \ --cpd_instance_ns=${PROJECT_CPD_INST_OPERANDS} \ --block_storage_class=${STG_CLASS_BLOCK} \ --file_storage_class=${STG_CLASS_FILE} \ ---license_acceptance=true +--license_acceptance=true \ +--case_download=true \ +--from_oci=true ``` -## Verifying the installation -```tsx -cpd-cli manage get-cr-status \ ---cpd_instance_ns=${PROJECT_CPD_INST_OPERANDS} \ ---components=watsonx_ai +### Install Additional Models: + +This installs the following models: + +granite-13b-instruct-v2 +llama-2-70b-chat +mixtral-8x7b-instruct-v01-q + +Run the following command: + +``` +oc patch watsonxaiifm watsonxaiifm-cr \ +--namespace=${PROJECT_CPD_INST_OPERANDS} \ +--type=merge \ +--patch='{"spec":{"install_model_list": ["ibm-mistralai-mixtral-8x7b-instruct-v01-q","ibm-granite-13b-chat-v2","meta-llama-llama-2-70b-chat"]}}' ``` + +