Node labeller flags for partition related labels[DO NOT MERGE]

api/v1alpha1/deviceconfig_types.go

@@ -94,7 +94,9 @@ type DriverSpec struct {
 	// +kubebuilder:default=true
 	Enable *bool `json:"enable,omitempty"`
 
-	// blacklist amdgpu drivers on the host
+	// blacklist amdgpu drivers on the host. Node reboot is required to apply the baclklist on the worker nodes.
+	// Not working for OpenShift cluster. OpenShift users please use the Machine Config Operator (MCO) resource to configure amdgpu blacklist.
+	// Example MCO resource is available at https://instinct.docs.amd.com/projects/gpu-operator/en/latest/installation/openshift-olm.html#create-blacklist-for-installing-out-of-tree-kernel-module
 	//+operator-sdk:csv:customresourcedefinitions:type=spec,displayName="BlacklistDrivers",xDescriptors={"urn:alm:descriptor:com.amd.deviceconfigs:blacklistDrivers"}
 	Blacklist *bool `json:"blacklist,omitempty"`
 
@@ -115,6 +117,7 @@ type DriverSpec struct {
 	// for OpenShift the default value is image-registry.openshift-image-registry.svc:5000/$MOD_NAMESPACE/amdgpu_kmod
 	// image tag will be in the format of <linux distro>-<release version>-<kernel version>-<driver version>
 	// example tag is coreos-416.94-5.14.0-427.28.1.el9_4.x86_64-6.2.2 and ubuntu-22.04-5.15.0-94-generic-6.1.3
+	// NOTE: Updating the driver image repository is not supported. Please delete the existing DeviceConfig and create a new one with the updated image repository
 	//+operator-sdk:csv:customresourcedefinitions:type=spec,displayName="Image",xDescriptors={"urn:alm:descriptor:com.amd.deviceconfigs:image"}
 	// +optional
 	// +kubebuilder:validation:Pattern=`^([a-z0-9]+(?:[._-][a-z0-9]+)*(:[0-9]+)?)(/[$a-zA-Z0-9_]+(?:[._-][$a-zA-Z0-9_]+)*)*(?::[a-z0-9._-]+)?(?:@[a-zA-Z0-9]+:[a-f0-9]+)?$`
@@ -595,6 +598,7 @@ type ModuleStatus struct {
 	LastTransitionTime string       `json:"lastTransitionTime,omitempty"`
 	Status             UpgradeState `json:"status,omitempty"`
 	UpgradeStartTime   string       `json:"upgradeStartTime,omitempty"`
+	BootId             string       `json:"bootId,omitempty"`
 }
 
 // DeviceConfigStatus defines the observed state of Module.

bundle/manifests/amd-gpu-operator.clusterserviceversion.yaml

@@ -29,12 +29,30 @@ metadata:
           }
         }
       ]
-    capabilities: Basic Install
-    createdAt: "2025-03-25T06:19:27Z"
+    capabilities: Seamless Upgrades
+    categories: AI/Machine Learning,Monitoring
+    containerImage: docker.io/rocm/gpu-operator:v1.2.0
+    createdAt: "2025-04-10T00:25:51Z"
+    description: |-
+      Operator responsible for deploying AMD GPU kernel drivers, device plugin, device test runner and device metrics exporter
+      For more information, visit [documentation](https://instinct.docs.amd.com/projects/gpu-operator/en/latest/)
+    devicePluginImage: docker.io/rocm/k8s-device-plugin:rhubi-latest
+    features.operators.openshift.io/disconnected: "true"
+    features.operators.openshift.io/fips-compliant: "false"
+    features.operators.openshift.io/proxy-aware: "true"
+    features.operators.openshift.io/tls-profiles: "false"
+    features.operators.openshift.io/token-auth-aws: "false"
+    features.operators.openshift.io/token-auth-azure: "false"
+    features.operators.openshift.io/token-auth-gcp: "false"
+    metricsExporterImage: docker.io/rocm/device-metrics-exporter:v1.2.0
+    nodelabellerImage: docker.io/rocm/k8s-device-plugin:labeller-rhubi-latest
+    operatorframework.io/cluster-monitoring: "true"
     operatorframework.io/suggested-namespace: openshift-amd-gpu
+    operators.openshift.io/valid-subscription: '[]'
     operators.operatorframework.io/builder: operator-sdk-v1.32.0
     operators.operatorframework.io/project_layout: go.kubebuilder.io/v3
     repository: https://github.com/ROCm/gpu-operator
+    support: Advanced Micro Devices, Inc.
   name: amd-gpu-operator.v1.2.0
   namespace: placeholder
 spec:
@@ -229,7 +247,10 @@ spec:
         path: driver.amdgpuInstallerRepoURL
         x-descriptors:
         - urn:alm:descriptor:com.amd.deviceconfigs:amdgpuInstallerRepoURL
-      - description: blacklist amdgpu drivers on the host
+      - description: blacklist amdgpu drivers on the host. Node reboot is required
+          to apply the baclklist on the worker nodes. Not working for OpenShift cluster.
+          OpenShift users please use the Machine Config Operator (MCO) resource to
+          configure amdgpu blacklist. Example MCO resource is available at https://instinct.docs.amd.com/projects/gpu-operator/en/latest/installation/openshift-olm.html#create-blacklist-for-installing-out-of-tree-kernel-module
         displayName: BlacklistDrivers
         path: driver.blacklist
         x-descriptors:
@@ -241,13 +262,15 @@ spec:
         path: driver.enable
         x-descriptors:
         - urn:alm:descriptor:com.amd.deviceconfigs:enable
-      - description: defines image that includes drivers and firmware blobs, don't
+      - description: 'defines image that includes drivers and firmware blobs, don''t
           include tag since it will be fully managed by operator for vanilla k8s the
           default value is image-registry:5000/$MOD_NAMESPACE/amdgpu_kmod for OpenShift
           the default value is image-registry.openshift-image-registry.svc:5000/$MOD_NAMESPACE/amdgpu_kmod
           image tag will be in the format of <linux distro>-<release version>-<kernel
           version>-<driver version> example tag is coreos-416.94-5.14.0-427.28.1.el9_4.x86_64-6.2.2
-          and ubuntu-22.04-5.15.0-94-generic-6.1.3
+          and ubuntu-22.04-5.15.0-94-generic-6.1.3 NOTE: Updating the driver image
+          repository is not supported. Please delete the existing DeviceConfig and
+          create a new one with the updated image repository'
         displayName: Image
         path: driver.image
         x-descriptors:
@@ -608,7 +631,7 @@ spec:
         - urn:alm:descriptor:com.amd.deviceconfigs:nodeModuleStatus
       version: v1alpha1
   description: |-
-    Operator responsible for deploying AMD GPU kernel drivers and device plugin
+    Operator responsible for deploying AMD GPU kernel drivers, device plugin, device test runner and device metrics exporter
     For more information, visit [documentation](https://instinct.docs.amd.com/projects/gpu-operator/en/latest/)
   displayName: amd-gpu-operator
   icon:
@@ -1112,11 +1135,24 @@ spec:
   - supported: true
     type: AllNamespaces
   keywords:
-  - amd-gpu-operator
+  - AMD
+  - GPU
+  - AI
+  - Deep Learning
+  - Hardware
+  - Driver
+  - Monitoring
   links:
-  - name: Amd Gpu Operator
-    url: https://amd-gpu-operator.domain
-  maturity: alpha
+  - name: AMD GPU Operator
+    url: https://github.com/ROCm/gpu-operator
+  maintainers:
+  - email: Yan.Sun3@amd.com
+    name: Yan Sun
+  - email: farshad.ghodsian@amd.com
+    name: Farshad Ghodsian
+  - email: shrey.ajmera@amd.com
+    name: Shrey Ajmera
+  maturity: stable
   provider:
-    name: amd-gpu-operator
+    name: Advanced Micro Devices, Inc.
   version: 1.2.0

bundle/manifests/amd.com_deviceconfigs.yaml

@@ -342,7 +342,10 @@ spec:
                       installer URL is https://repo.radeon.com/amdgpu-install by default
                     type: string
                   blacklist:
-                    description: blacklist amdgpu drivers on the host
+                    description: |-
+                      blacklist amdgpu drivers on the host. Node reboot is required to apply the baclklist on the worker nodes.
+                      Not working for OpenShift cluster. OpenShift users please use the Machine Config Operator (MCO) resource to configure amdgpu blacklist.
+                      Example MCO resource is available at https://instinct.docs.amd.com/projects/gpu-operator/en/latest/installation/openshift-olm.html#create-blacklist-for-installing-out-of-tree-kernel-module
                     type: boolean
                   enable:
                     default: true
@@ -357,6 +360,7 @@ spec:
                       for OpenShift the default value is image-registry.openshift-image-registry.svc:5000/$MOD_NAMESPACE/amdgpu_kmod
                       image tag will be in the format of <linux distro>-<release version>-<kernel version>-<driver version>
                       example tag is coreos-416.94-5.14.0-427.28.1.el9_4.x86_64-6.2.2 and ubuntu-22.04-5.15.0-94-generic-6.1.3
+                      NOTE: Updating the driver image repository is not supported. Please delete the existing DeviceConfig and create a new one with the updated image repository
                     pattern: ^([a-z0-9]+(?:[._-][a-z0-9]+)*(:[0-9]+)?)(/[$a-zA-Z0-9_]+(?:[._-][$a-zA-Z0-9_]+)*)*(?::[a-z0-9._-]+)?(?:@[a-zA-Z0-9]+:[a-f0-9]+)?$
                     type: string
                   imageRegistrySecret:
@@ -928,6 +932,8 @@ spec:
                   description: ModuleStatus contains the status of driver module installed
                     by operator on the node
                   properties:
+                    bootId:
+                      type: string
                     containerImage:
                       type: string
                     kernelVersion:

config/crd/bases/amd.com_deviceconfigs.yaml

@@ -338,7 +338,10 @@ spec:
                       installer URL is https://repo.radeon.com/amdgpu-install by default
                     type: string
                   blacklist:
-                    description: blacklist amdgpu drivers on the host
+                    description: |-
+                      blacklist amdgpu drivers on the host. Node reboot is required to apply the baclklist on the worker nodes.
+                      Not working for OpenShift cluster. OpenShift users please use the Machine Config Operator (MCO) resource to configure amdgpu blacklist.
+                      Example MCO resource is available at https://instinct.docs.amd.com/projects/gpu-operator/en/latest/installation/openshift-olm.html#create-blacklist-for-installing-out-of-tree-kernel-module
                     type: boolean
                   enable:
                     default: true
@@ -353,6 +356,7 @@ spec:
                       for OpenShift the default value is image-registry.openshift-image-registry.svc:5000/$MOD_NAMESPACE/amdgpu_kmod
                       image tag will be in the format of <linux distro>-<release version>-<kernel version>-<driver version>
                       example tag is coreos-416.94-5.14.0-427.28.1.el9_4.x86_64-6.2.2 and ubuntu-22.04-5.15.0-94-generic-6.1.3
+                      NOTE: Updating the driver image repository is not supported. Please delete the existing DeviceConfig and create a new one with the updated image repository
                     pattern: ^([a-z0-9]+(?:[._-][a-z0-9]+)*(:[0-9]+)?)(/[$a-zA-Z0-9_]+(?:[._-][$a-zA-Z0-9_]+)*)*(?::[a-z0-9._-]+)?(?:@[a-zA-Z0-9]+:[a-f0-9]+)?$
                     type: string
                   imageRegistrySecret:
@@ -924,6 +928,8 @@ spec:
                   description: ModuleStatus contains the status of driver module installed
                     by operator on the node
                   properties:
+                    bootId:
+                      type: string
                     containerImage:
                       type: string
                     kernelVersion:

config/manifests/bases/amd-gpu-operator.clusterserviceversion.yaml

@@ -3,9 +3,27 @@ kind: ClusterServiceVersion
 metadata:
   annotations:
     alm-examples: '[]'
-    capabilities: Basic Install
+    capabilities: Seamless Upgrades
+    categories: AI/Machine Learning,Monitoring
+    containerImage: docker.io/rocm/gpu-operator:v1.2.0
+    description: |-
+      Operator responsible for deploying AMD GPU kernel drivers, device plugin, device test runner and device metrics exporter
+      For more information, visit [documentation](https://instinct.docs.amd.com/projects/gpu-operator/en/latest/)
+    devicePluginImage: docker.io/rocm/k8s-device-plugin:rhubi-latest
+    features.operators.openshift.io/disconnected: "true"
+    features.operators.openshift.io/fips-compliant: "false"
+    features.operators.openshift.io/proxy-aware: "true"
+    features.operators.openshift.io/tls-profiles: "false"
+    features.operators.openshift.io/token-auth-aws: "false"
+    features.operators.openshift.io/token-auth-azure: "false"
+    features.operators.openshift.io/token-auth-gcp: "false"
+    metricsExporterImage: docker.io/rocm/device-metrics-exporter:v1.2.0
+    nodelabellerImage: docker.io/rocm/k8s-device-plugin:labeller-rhubi-latest
+    operatorframework.io/cluster-monitoring: "true"
     operatorframework.io/suggested-namespace: openshift-amd-gpu
+    operators.openshift.io/valid-subscription: '[]'
     repository: https://github.com/ROCm/gpu-operator
+    support: Advanced Micro Devices, Inc.
   name: amd-gpu-operator.v0.0.0
   namespace: placeholder
 spec:
@@ -200,7 +218,10 @@ spec:
         path: driver.amdgpuInstallerRepoURL
         x-descriptors:
         - urn:alm:descriptor:com.amd.deviceconfigs:amdgpuInstallerRepoURL
-      - description: blacklist amdgpu drivers on the host
+      - description: blacklist amdgpu drivers on the host. Node reboot is required
+          to apply the baclklist on the worker nodes. Not working for OpenShift cluster.
+          OpenShift users please use the Machine Config Operator (MCO) resource to
+          configure amdgpu blacklist. Example MCO resource is available at https://instinct.docs.amd.com/projects/gpu-operator/en/latest/installation/openshift-olm.html#create-blacklist-for-installing-out-of-tree-kernel-module
         displayName: BlacklistDrivers
         path: driver.blacklist
         x-descriptors:
@@ -212,13 +233,15 @@ spec:
         path: driver.enable
         x-descriptors:
         - urn:alm:descriptor:com.amd.deviceconfigs:enable
-      - description: defines image that includes drivers and firmware blobs, don't
+      - description: 'defines image that includes drivers and firmware blobs, don''t
           include tag since it will be fully managed by operator for vanilla k8s the
           default value is image-registry:5000/$MOD_NAMESPACE/amdgpu_kmod for OpenShift
           the default value is image-registry.openshift-image-registry.svc:5000/$MOD_NAMESPACE/amdgpu_kmod
           image tag will be in the format of <linux distro>-<release version>-<kernel
           version>-<driver version> example tag is coreos-416.94-5.14.0-427.28.1.el9_4.x86_64-6.2.2
-          and ubuntu-22.04-5.15.0-94-generic-6.1.3
+          and ubuntu-22.04-5.15.0-94-generic-6.1.3 NOTE: Updating the driver image
+          repository is not supported. Please delete the existing DeviceConfig and
+          create a new one with the updated image repository'
         displayName: Image
         path: driver.image
         x-descriptors:
@@ -579,7 +602,7 @@ spec:
         - urn:alm:descriptor:com.amd.deviceconfigs:nodeModuleStatus
       version: v1alpha1
   description: |-
-    Operator responsible for deploying AMD GPU kernel drivers and device plugin
+    Operator responsible for deploying AMD GPU kernel drivers, device plugin, device test runner and device metrics exporter
     For more information, visit [documentation](https://instinct.docs.amd.com/projects/gpu-operator/en/latest/)
   displayName: amd-gpu-operator
   icon:
@@ -599,11 +622,24 @@ spec:
   - supported: true
     type: AllNamespaces
   keywords:
-  - amd-gpu-operator
+  - AMD
+  - GPU
+  - AI
+  - Deep Learning
+  - Hardware
+  - Driver
+  - Monitoring
   links:
-  - name: Amd Gpu Operator
-    url: https://amd-gpu-operator.domain
-  maturity: alpha
+  - name: AMD GPU Operator
+    url: https://github.com/ROCm/gpu-operator
+  maintainers:
+  - email: Yan.Sun3@amd.com
+    name: Yan Sun
+  - email: farshad.ghodsian@amd.com
+    name: Farshad Ghodsian
+  - email: shrey.ajmera@amd.com
+    name: Shrey Ajmera
+  maturity: stable
   provider:
-    name: amd-gpu-operator
+    name: Advanced Micro Devices, Inc.
   version: 0.0.0

docs/conf.py

@@ -1,26 +1,32 @@
 """Configuration file for the Sphinx documentation builder."""
+import os
 
+html_baseurl = os.environ.get("READTHEDOCS_CANONICAL_URL", "instinct.docs.amd.com")
+html_context = {}
+if os.environ.get("READTHEDOCS", "") == "True":
+    html_context["READTHEDOCS"] = True
 external_projects_local_file = "projects.yaml"
 external_projects_remote_repository = ""
 external_projects = ["amd-gpu-operator"]
 external_projects_current_project = "amd-gpu-operator"
 
-project = "AMD Instinct Documentation"
+project = "AMD GPU Operator"
 version = "1.2.0"
 release = version
-html_title = f"AMD GPU Operator {version}"
+html_title = f"{project} {version}"
 author = "Advanced Micro Devices, Inc."
-copyright = "Copyright (c) 2024 Advanced Micro Devices, Inc. All rights reserved."
+copyright = "Copyright (c) 2025 Advanced Micro Devices, Inc. All rights reserved."
 
 # Required settings
 html_theme = "rocm_docs_theme"
 html_theme_options = {
-    "flavor": "instinct"
+    "flavor": "instinct",
+    "link_main_doc": True,
     # Add any additional theme options here
 }
 extensions = ["rocm_docs"]
 
 # Table of contents
 external_toc_path = "./sphinx/_toc.yml"
 
-exclude_patterns = ['.venv']
+exclude_patterns = ['.venv']