Merge branch 'NVIDIA:main' into helm-docs

.github/workflows/golang.yaml

@@ -40,11 +40,16 @@ jobs:
         args: -v --timeout 5m
         skip-cache: true
 
-    - name: Check golang modules
+    - name: Golang modules
       run: |
         make check-modules
         make -C deployments/devel check-modules
 
+    - name: Generated code
+      run: |
+        make -C deployments/devel install-tools
+        make check-generate
+
   test:
     name: Unit test
     runs-on: ubuntu-latest

Makefile

@@ -30,7 +30,7 @@ endif
 CMDS := $(patsubst ./cmd/%/,%,$(sort $(dir $(wildcard ./cmd/*/))))
 CMD_TARGETS := $(patsubst %,cmd-%, $(CMDS))
 
-CHECK_TARGETS := golangci-lint
+CHECK_TARGETS := golangci-lint check-generate
 MAKE_TARGETS := binaries build build-image check fmt lint-internal test examples cmds coverage generate vendor check-modules $(CHECK_TARGETS)
 
 TARGETS := $(MAKE_TARGETS) $(CMD_TARGETS)
@@ -113,6 +113,9 @@ generate-crds: generate-deepcopy .remove-crds
 	rm -rf $(CURDIR)/deployments/helm/tmp_crds
 
 
+check-generate: generate
+	git diff --exit-code HEAD
+
 generate-deepcopy: .remove-deepcopy
 	for dir in $(DEEPCOPY_SOURCES); do \
 		controller-gen \

demo/specs/imex/README.sh

@@ -20,6 +20,7 @@ helm upgrade -i \
 	nvidia-dra-driver-gpu \
 	../../../deployments/helm/nvidia-dra-driver-gpu \
     --set nvidiaDriverRoot="/" \
+    --set nvidiaCtkPath=/usr/local/nvidia/toolkit/nvidia-ctk \
 	--set resources.gpus.enabled=false \
     --wait
 

deployments/container/Dockerfile

@@ -14,7 +14,7 @@
 
 ARG GOLANG_VERSION=1.23.1
 # We use an ubuntu20.04 base image to allow for a more efficient multi-arch builds.
-FROM --platform=${BUILDOS}/amd64 nvcr.io/nvidia/cuda:12.3.2-base-ubuntu20.04 AS build
+FROM --platform=${BUILDOS}/amd64 nvcr.io/nvidia/cuda:12.8.0-base-ubuntu20.04 AS build
 
 RUN apt-get update && \
     apt-get install -y wget make git gcc-aarch64-linux-gnu gcc \
@@ -43,7 +43,7 @@ RUN if [ "$TARGETARCH" = "amd64" ]; then \
     fi && \
     make CC=${cc} GOARCH=${TARGETARCH} PREFIX=/artifacts cmds
 
-FROM nvcr.io/nvidia/cuda:12.3.2-base-ubi9
+FROM nvcr.io/nvidia/cuda:12.8.0-base-ubi9
 
 ENV NVIDIA_DISABLE_REQUIRE="true"
 ENV NVIDIA_VISIBLE_DEVICES=all

deployments/helm/nvidia-dra-driver-gpu/Chart.yaml

@@ -15,10 +15,10 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: v25.2.0
+version: v25.3.0
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
 # follow Semantic Versioning. They should reflect the version the application is using.
 # It is recommended to use it with quotes.
-appVersion: "v25.2.0"
+appVersion: "v25.3.0"

go.mod

@@ -24,7 +24,7 @@ require (
 	k8s.io/kubernetes v1.32.0
 	k8s.io/mount-utils v0.32.0
 	k8s.io/utils v0.0.0-20241104100929-3ea5e8cea738
-	tags.cncf.io/container-device-interface v0.8.0
+	tags.cncf.io/container-device-interface v0.8.1
 	tags.cncf.io/container-device-interface/specs-go v0.8.0
 )
 

go.sum

@@ -261,7 +261,7 @@ sigs.k8s.io/structured-merge-diff/v4 v4.4.2 h1:MdmvkGuXi/8io6ixD5wud3vOLwc1rj0aN
 sigs.k8s.io/structured-merge-diff/v4 v4.4.2/go.mod h1:N8f93tFZh9U6vpxwRArLiikrE5/2tiu1w1AGfACIGE4=
 sigs.k8s.io/yaml v1.4.0 h1:Mk1wCc2gy/F0THH0TAp1QYyJNzRm2KCLy3o5ASXVI5E=
 sigs.k8s.io/yaml v1.4.0/go.mod h1:Ejl7/uTz7PSA4eKMyQCUTnhZYNmLIl+5c2lQPGR2BPY=
-tags.cncf.io/container-device-interface v0.8.0 h1:8bCFo/g9WODjWx3m6EYl3GfUG31eKJbaggyBDxEldRc=
-tags.cncf.io/container-device-interface v0.8.0/go.mod h1:Apb7N4VdILW0EVdEMRYXIDVRZfNJZ+kmEUss2kRRQ6Y=
+tags.cncf.io/container-device-interface v0.8.1 h1:c0jN4Mt6781jD67NdPajmZlD1qrqQyov/Xfoab37lj0=
+tags.cncf.io/container-device-interface v0.8.1/go.mod h1:Apb7N4VdILW0EVdEMRYXIDVRZfNJZ+kmEUss2kRRQ6Y=
 tags.cncf.io/container-device-interface/specs-go v0.8.0 h1:QYGFzGxvYK/ZLMrjhvY0RjpUavIn4KcmRmVP/JjdBTA=
 tags.cncf.io/container-device-interface/specs-go v0.8.0/go.mod h1:BhJIkjjPh4qpys+qm4DAYtUyryaTDg9zris+AczXyws=

hack/package-helm-charts.sh

@@ -0,0 +1,28 @@
+#!/usr/bin/env bash
+
+# Copyright (c) 2025, NVIDIA CORPORATION.  All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+set -o pipefail
+
+# if arg1 is set, it will be used as the version number
+if [ -z "$1" ]; then
+  VERSION=$(awk -F= '/^VERSION/ { print $2 }' versions.mk | tr -d '[:space:]')
+else
+  VERSION=$1
+fi
+VERSION=${VERSION}
+
+# Create release assets to be uploaded
+helm package deployments/helm/nvidia-dra-driver-gpu/ --version $VERSION --app-version $VERSION

vendor/modules.txt

@@ -825,7 +825,7 @@ sigs.k8s.io/structured-merge-diff/v4/value
 ## explicit; go 1.12
 sigs.k8s.io/yaml
 sigs.k8s.io/yaml/goyaml.v2
-# tags.cncf.io/container-device-interface v0.8.0
+# tags.cncf.io/container-device-interface v0.8.1
 ## explicit; go 1.20
 tags.cncf.io/container-device-interface/internal/validation
 tags.cncf.io/container-device-interface/internal/validation/k8s

versions.mk

@@ -18,7 +18,7 @@ MODULE := github.com/NVIDIA/$(DRIVER_NAME)
 
 REGISTRY ?= nvcr.io/nvidia/cloud-native
 
-VERSION  ?= v25.2.0
+VERSION  ?= v25.3.0
 
 # vVERSION represents the version with a guaranteed v-prefix
 vVERSION := v$(VERSION:v%=%)