Merge pull request #653 from elezar/bump-v0.15.0

Bump version to v0.15.0

Author: elezar

CHANGELOG.md

@@ -1,5 +1,13 @@
 ## Changelog
 
+### Version v0.15.0
+- Moved `nvidia-device-plugin.yml` static deployment at the root of the repository to `deployments/static/nvidia-device-plugin.yml`.
+- Simplify PCI device clases in NFD worker configuration.
+- Update CUDA base image version to 12.4.1.
+- Switch to Ubuntu22.04-based CUDA image for default image.
+- Add new CUDA driver and runtime version labels to align with other NFD version labels.
+- Update NFD dependency to v0.15.3.
+
 ### Version v0.15.0-rc.2
 - Bump CUDA base image version to 12.3.2
 - Add `cdi-cri` device list strategy. This uses the CDIDevices CRI field to request CDI devices instead of annotations.

README.md

@@ -123,7 +123,7 @@ Once you have configured the options above on all the GPU nodes in your
 cluster, you can enable GPU support by deploying the following Daemonset:
 
 ```shell
-$ kubectl create -f https://raw.githubusercontent.com/NVIDIA/k8s-device-plugin/v0.14.5/deployments/static/nvidia-device-plugin.yml
+$ kubectl create -f https://raw.githubusercontent.com/NVIDIA/k8s-device-plugin/v0.15.0/deployments/static/nvidia-device-plugin.yml
 ```
 
 **Note:** This is a simple static daemonset meant to demonstrate the basic

RELEASE.md

@@ -9,7 +9,7 @@ Publishing the helm chart is currently manual, and we should move to an automate
 
 # Release Process Checklist
 - [ ] Update the README changelog
-- [ ] Update the README to change occurances of the old version (e.g: `v0.14.5`) with the new version
+- [ ] Update the README to change occurances of the old version (e.g: `v0.15.0`) with the new version
 - [ ] Commit, Tag and Push to Gitlab
 - [ ] Build a new helm package with `./hack/package-helm-charts.sh`
 - [ ] Switch to the `gh-pages` branch and move the newly generated package to the `stable` helm repo

deployments/helm/nvidia-device-plugin/Chart.yaml

@@ -2,8 +2,8 @@ apiVersion: v2
 name: nvidia-device-plugin
 type: application
 description: A Helm chart for the nvidia-device-plugin on Kubernetes
-version: "0.15.0-rc.2"
-appVersion: "0.15.0-rc.2"
+version: "0.15.0"
+appVersion: "0.15.0"
 kubeVersion: ">= 1.10.0-0"
 home: https://github.com/NVIDIA/k8s-device-plugin
 

deployments/static/gpu-feature-discovery-daemonset-with-mig-mixed.yaml

@@ -4,7 +4,7 @@ metadata:
   name: gpu-feature-discovery
   labels:
     app.kubernetes.io/name: gpu-feature-discovery
-    app.kubernetes.io/version: 0.15.0-rc.2
+    app.kubernetes.io/version: 0.15.0
     app.kubernetes.io/part-of: nvidia-gpu
 spec:
   selector:
@@ -15,11 +15,11 @@ spec:
     metadata:
       labels:
         app.kubernetes.io/name: gpu-feature-discovery
-        app.kubernetes.io/version: 0.15.0-rc.2
+        app.kubernetes.io/version: 0.15.0
         app.kubernetes.io/part-of: nvidia-gpu
     spec:
       containers:
-        - image: nvcr.io/nvidia/k8s-device-plugin:v0.15.0-rc.2
+        - image: nvcr.io/nvidia/k8s-device-plugin:v0.15.0
           name: gpu-feature-discovery
           command: ["/usr/bin/gpu-feature-discovery"]
           volumeMounts:

deployments/static/gpu-feature-discovery-daemonset-with-mig-single.yaml

@@ -4,7 +4,7 @@ metadata:
   name: gpu-feature-discovery
   labels:
     app.kubernetes.io/name: gpu-feature-discovery
-    app.kubernetes.io/version: 0.15.0-rc.2
+    app.kubernetes.io/version: 0.15.0
     app.kubernetes.io/part-of: nvidia-gpu
 spec:
   selector:
@@ -15,11 +15,11 @@ spec:
     metadata:
       labels:
         app.kubernetes.io/name: gpu-feature-discovery
-        app.kubernetes.io/version: 0.15.0-rc.2
+        app.kubernetes.io/version: 0.15.0
         app.kubernetes.io/part-of: nvidia-gpu
     spec:
       containers:
-        - image: nvcr.io/nvidia/k8s-device-plugin:v0.15.0-rc.2
+        - image: nvcr.io/nvidia/k8s-device-plugin:v0.15.0
           name: gpu-feature-discovery
           command: ["/usr/bin/gpu-feature-discovery"]
           volumeMounts:

deployments/static/gpu-feature-discovery-daemonset.yaml

@@ -4,7 +4,7 @@ metadata:
   name: gpu-feature-discovery
   labels:
     app.kubernetes.io/name: gpu-feature-discovery
-    app.kubernetes.io/version: 0.15.0-rc.2
+    app.kubernetes.io/version: 0.15.0
     app.kubernetes.io/part-of: nvidia-gpu
 spec:
   selector:
@@ -15,11 +15,11 @@ spec:
     metadata:
       labels:
         app.kubernetes.io/name: gpu-feature-discovery
-        app.kubernetes.io/version: 0.15.0-rc.2
+        app.kubernetes.io/version: 0.15.0
         app.kubernetes.io/part-of: nvidia-gpu
     spec:
       containers:
-        - image: nvcr.io/nvidia/k8s-device-plugin:v0.15.0-rc.2
+        - image: nvcr.io/nvidia/k8s-device-plugin:v0.15.0
           name: gpu-feature-discovery
           command: ["/usr/bin/gpu-feature-discovery"]
           volumeMounts:

deployments/static/gpu-feature-discovery-job.yaml.template

@@ -4,19 +4,19 @@ metadata:
   name: gpu-feature-discovery
   labels:
     app.kubernetes.io/name: gpu-feature-discovery
-    app.kubernetes.io/version: 0.15.0-rc.2
+    app.kubernetes.io/version: 0.15.0
     app.kubernetes.io/part-of: nvidia-gpu
 spec:
   template:
     metadata:
       labels:
         app.kubernetes.io/name: gpu-feature-discovery
-        app.kubernetes.io/version: 0.15.0-rc.2
+        app.kubernetes.io/version: 0.15.0
         app.kubernetes.io/part-of: nvidia-gpu
     spec:
       nodeName: NODE_NAME
       containers:
-        - image: nvcr.io/nvidia/k8s-device-plugin:v0.15.0-rc.2
+        - image: nvcr.io/nvidia/k8s-device-plugin:v0.15.0
           name: gpu-feature-discovery
           command: ["/usr/bin/gpu-feature-discovery"]
           args:

deployments/static/nvidia-device-plugin-compat-with-cpumanager.yml

@@ -38,7 +38,7 @@ spec:
       # See https://kubernetes.io/docs/tasks/administer-cluster/guaranteed-scheduling-critical-addon-pods/
       priorityClassName: "system-node-critical"
       containers:
-      - image: nvcr.io/nvidia/k8s-device-plugin:v0.15.0-rc.2
+      - image: nvcr.io/nvidia/k8s-device-plugin:v0.15.0
         name: nvidia-device-plugin-ctr
         env:
           - name: FAIL_ON_INIT_ERROR

deployments/static/nvidia-device-plugin-privileged-with-service-account.yml

@@ -124,7 +124,7 @@ spec:
         - env:
             - name: PASS_DEVICE_SPECS
               value: "true"
-          image: nvcr.io/nvidia/k8s-device-plugin:v0.15.0-rc.2
+          image: nvcr.io/nvidia/k8s-device-plugin:v0.15.0
           name: nvidia-device-plugin-ctr
           securityContext:
             privileged: true

deployments/static/nvidia-device-plugin.yml

@@ -38,7 +38,7 @@ spec:
       # See https://kubernetes.io/docs/tasks/administer-cluster/guaranteed-scheduling-critical-addon-pods/
       priorityClassName: "system-node-critical"
       containers:
-      - image: nvcr.io/nvidia/k8s-device-plugin:v0.15.0-rc.2
+      - image: nvcr.io/nvidia/k8s-device-plugin:v0.15.0
         name: nvidia-device-plugin-ctr
         env:
           - name: FAIL_ON_INIT_ERROR

versions.mk

@@ -17,7 +17,7 @@ MODULE := github.com/NVIDIA/$(DRIVER_NAME)
 
 REGISTRY ?= nvcr.io/nvidia
 
-VERSION  ?= v0.15.0-rc.2
+VERSION  ?= v0.15.0
 
 # vVERSION represents the version with a guaranteed v-prefix
 vVERSION := v$(VERSION:v%=%)