CI/CD: Add CUDA version to docker image tags

.azure/gpu-benchmark.yml

@@ -28,7 +28,7 @@ jobs:
     cancelTimeoutInMinutes: "2"
     pool: azure-jirka-spot
     container:
-      image: "pytorchlightning/pytorch_lightning:base-cuda-py3.9-torch1.12"
+      image: "pytorchlightning/pytorch_lightning:base-cuda-py3.9-torch1.12-cuda11.3.1"
       options: "--runtime=nvidia -e NVIDIA_VISIBLE_DEVICES=all --shm-size=32g"
     workspace:
       clean: all

.azure/gpu-tests.yml

@@ -26,7 +26,7 @@ jobs:
     strategy:
       matrix:
         'PyTorch - stable':
-          image: "pytorchlightning/pytorch_lightning:base-cuda-py3.9-torch1.12"
+          image: "pytorchlightning/pytorch_lightning:base-cuda-py3.9-torch1.12-cuda11.3.1"
     # how long to run the job before automatically cancelling
     timeoutInMinutes: "80"
     # how much time to give 'run always even if cancelled tasks' before stopping them
@@ -44,7 +44,7 @@ jobs:
 
     - bash: |
         CHANGED_FILES=$(git diff --name-status origin/master -- . | awk  '{print $2}')
-        FILTER='src/pytorch_lightning|requirements/pytorch|tests/tests_pytorch|examples/pl_*|.azure/*'
+        FILTER='src/pytorch_lightning|requirements/pytorch|tests/tests_pytorch|examples/pl_*|.azure/gpu-*.yml'
         echo $CHANGED_FILES > changed_files.txt
         MATCHES=$(cat changed_files.txt | grep -E $FILTER)
         echo $MATCHES

.github/workflows/ci-pytorch_test-conda.yml

@@ -18,16 +18,16 @@ defaults:
 jobs:
   conda:
     runs-on: ubuntu-20.04
-    container: pytorchlightning/pytorch_lightning:base-conda-py${{ matrix.python-version }}-torch${{ matrix.pytorch-version }}
+    container: pytorchlightning/pytorch_lightning:base-conda-py${{ matrix.python-version }}-torch${{ matrix.pytorch-version }}-cuda${{ matrix.cuda-version }}
     strategy:
       fail-fast: false
       matrix:
         # nightly: add when there's a release candidate
         include:
-          - {python-version: "3.8", pytorch-version: "1.9"}
-          - {python-version: "3.8", pytorch-version: "1.10"}
-          - {python-version: "3.9", pytorch-version: "1.11"}
-          - {python-version: "3.9", pytorch-version: "1.12"}
+          - {python-version: "3.8", pytorch-version: "1.9", cuda-version: "11.1"}
+          - {python-version: "3.8", pytorch-version: "1.10", cuda-version: "11.1"}
+          - {python-version: "3.9", pytorch-version: "1.11", cuda-version: "11.3.1"}
+          - {python-version: "3.9", pytorch-version: "1.12", cuda-version: "11.3.1"}
 
     timeout-minutes: 30
 
@@ -45,7 +45,7 @@ jobs:
       id: skip
       shell: bash -l {0}
       run: |
-        FILTER='src/pytorch_lightning|requirements/pytorch|tests/tests_pytorch|examples/pl_*'
+        FILTER='src/pytorch_lightning|requirements/pytorch|tests/tests_pytorch|examples/pl_*|.github/workflows/ci-pytorch_test-conda.yml'
         echo "${{ steps.changed-files.outputs.all_changed_files }}" | tr " " "\n" > changed_files.txt
         MATCHES=$(cat changed_files.txt | grep -E $FILTER)
         echo $MATCHES

.github/workflows/cicd-pytorch_dockers.yml

@@ -21,25 +21,39 @@ concurrency:
   cancel-in-progress: ${{ ! (github.ref == 'refs/heads/master' || startsWith(github.ref, 'refs/heads/release/')) }}
 
 env:
-  PUSH_TO_HUB: ${{ github.event_name == 'schedule' }}
+  PUSH_TO_HUB: true
 
 jobs:
   build-pl:
     runs-on: ubuntu-20.04
     strategy:
       fail-fast: false
       matrix:
-        # the config used in '.azure-pipelines/gpu-tests.yml' since the Dockerfile uses the cuda image
-        python_version: ["3.9"]
-        pytorch_version: ["1.12"]
+        include:
+          # Include all Python and PyTorch versions that PL supports.
+          - {python_version: "3.7", pytorch_version: "1.9", cuda_version: "11.1.1"}
+          - {python_version: "3.7", pytorch_version: "1.10", cuda_version: "11.3.1"}
+          - {python_version: "3.7", pytorch_version: "1.11", cuda_version: "11.3.1"}
+          - {python_version: "3.7", pytorch_version: "1.12", cuda_version: "11.3.1"}
+          - {python_version: "3.8", pytorch_version: "1.9", cuda_version: "11.1.1"}
+          - {python_version: "3.8", pytorch_version: "1.10", cuda_version: "11.3.1"}
+          - {python_version: "3.8", pytorch_version: "1.11", cuda_version: "11.3.1"}
+          - {python_version: "3.8", pytorch_version: "1.12", cuda_version: "11.3.1"}
+          - {python_version: "3.9", pytorch_version: "1.9", cuda_version: "11.1.1"}
+          - {python_version: "3.9", pytorch_version: "1.10", cuda_version: "11.3.1"}
+          - {python_version: "3.9", pytorch_version: "1.11", cuda_version: "11.3.1"}
+          - {python_version: "3.9", pytorch_version: "1.12", cuda_version: "11.3.1"}
+          # - {python_version: "3.10", pytorch_version: "1.11", cuda_version: "11.3.1"}
+          # - {python_version: "3.10", pytorch_version: "1.12", cuda_version: "11.3.1"}
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - uses: docker/setup-buildx-action@v2
-      - uses: docker/build-push-action@v2
+      - uses: docker/build-push-action@v3
         with:
           build-args: |
             PYTHON_VERSION=${{ matrix.python_version }}
             PYTORCH_VERSION=${{ matrix.pytorch_version }}
+            CUDA_VERSION=${{ matrix.cuda_version }}
           file: dockers/release/Dockerfile
           push: false  # pushed in release-docker.yml only when PL is released
         timeout-minutes: 50
@@ -53,14 +67,14 @@ jobs:
         python_version: ["3.7"]
         xla_version: ["1.11"]
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - uses: docker/setup-buildx-action@v2
-      - uses: docker/login-action@v1
+      - uses: docker/login-action@v2
         if: env.PUSH_TO_HUB == 'true'
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
-      - uses: docker/build-push-action@v2
+      - uses: docker/build-push-action@v3
         with:
           build-args: |
             PYTHON_VERSION=${{ matrix.python_version }}
@@ -85,30 +99,39 @@ jobs:
       fail-fast: false
       matrix:
         include:
-          # the config used in '.azure-pipelines/gpu-tests.yml'
-          - {python_version: "3.9", pytorch_version: "1.12", cuda_version: "11.3.1", ubuntu_version: "20.04"}
-          # latest (used in Tutorials)
-          - {python_version: "3.8", pytorch_version: "1.9", cuda_version: "11.1", ubuntu_version: "20.04"}
-          - {python_version: "3.9", pytorch_version: "1.10", cuda_version: "11.1", ubuntu_version: "20.04"}
-          - {python_version: "3.9", pytorch_version: "1.11", cuda_version: "11.3.1", ubuntu_version: "20.04"}
+          # These are the base images for PL release docker image distributions,
+          # so include all Python and PyTorch versions that PL supports.
+          - {python_version: "3.7", pytorch_version: "1.9", cuda_version: "11.1.1"}
+          - {python_version: "3.7", pytorch_version: "1.10", cuda_version: "11.3.1"}
+          - {python_version: "3.7", pytorch_version: "1.11", cuda_version: "11.3.1"}
+          - {python_version: "3.7", pytorch_version: "1.12", cuda_version: "11.3.1"}
+          - {python_version: "3.8", pytorch_version: "1.9", cuda_version: "11.1.1"}
+          - {python_version: "3.8", pytorch_version: "1.10", cuda_version: "11.3.1"}
+          - {python_version: "3.8", pytorch_version: "1.11", cuda_version: "11.3.1"}
+          - {python_version: "3.8", pytorch_version: "1.12", cuda_version: "11.3.1"}
+          - {python_version: "3.9", pytorch_version: "1.9", cuda_version: "11.1.1"}
+          - {python_version: "3.9", pytorch_version: "1.10", cuda_version: "11.3.1"}
+          - {python_version: "3.9", pytorch_version: "1.11", cuda_version: "11.3.1"}
+          - {python_version: "3.9", pytorch_version: "1.12", cuda_version: "11.3.1"}
+          # - {python_version: "3.10", pytorch_version: "1.11", cuda_version: "11.3.1"}
+          # - {python_version: "3.10", pytorch_version: "1.12", cuda_version: "11.3.1"}
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - uses: docker/setup-buildx-action@v2
-      - uses: docker/login-action@v1
+      - uses: docker/login-action@v2
         if: env.PUSH_TO_HUB == 'true'
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
-      - uses: docker/build-push-action@v2
+      - uses: docker/build-push-action@v3
         with:
           build-args: |
             PYTHON_VERSION=${{ matrix.python_version }}
             PYTORCH_VERSION=${{ matrix.pytorch_version }}
             CUDA_VERSION=${{ matrix.cuda_version }}
-            UBUNTU_VERSION=${{ matrix.ubuntu_version }}
           file: dockers/base-cuda/Dockerfile
           push: ${{ env.PUSH_TO_HUB }}
-          tags: pytorchlightning/pytorch_lightning:base-cuda-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }}
+          tags: pytorchlightning/pytorch_lightning:base-cuda-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }}-cuda${{ matrix.cuda_version }}
         timeout-minutes: 95
       - uses: ravsamhq/notify-slack-action@v1
         if: failure() && env.PUSH_TO_HUB == 'true'
@@ -126,28 +149,28 @@ jobs:
       fail-fast: false
       matrix:
         include:
-          - {python_version: "3.8", pytorch_version: "1.9", cuda_version: "11.1"}
-          - {python_version: "3.8", pytorch_version: "1.10", cuda_version: "11.1"}
+          - {python_version: "3.8", pytorch_version: "1.9", cuda_version: "11.1.1"}
+          - {python_version: "3.8", pytorch_version: "1.10", cuda_version: "11.1.1"}
           - {python_version: "3.9", pytorch_version: "1.11", cuda_version: "11.3.1"}
-          #  nightly: add when there's a release candidate
-          #  - {python_version: "3.9", pytorch_version: "1.12"}
+          - {python_version: "3.9", pytorch_version: "1.12", cuda_version: "11.3.1"}
+          # - {python_version: "3.10", pytorch_version: "1.12", cuda_version: "11.6.0"}
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - uses: docker/setup-buildx-action@v2
-      - uses: docker/login-action@v1
+      - uses: docker/login-action@v2
         if: env.PUSH_TO_HUB == 'true'
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
-      - uses: docker/build-push-action@v2
+      - uses: docker/build-push-action@v3
         with:
           build-args: |
             PYTHON_VERSION=${{ matrix.python_version }}
             PYTORCH_VERSION=${{ matrix.pytorch_version }}
             CUDA_VERSION=${{ matrix.cuda_version }}
           file: dockers/base-conda/Dockerfile
           push: ${{ env.PUSH_TO_HUB }}
-          tags: pytorchlightning/pytorch_lightning:base-conda-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }}
+          tags: pytorchlightning/pytorch_lightning:base-conda-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }}-cuda${{ matrix.cuda_version }}
         timeout-minutes: 95
       - uses: ravsamhq/notify-slack-action@v1
         if: failure() && env.PUSH_TO_HUB == 'true'
@@ -168,14 +191,14 @@ jobs:
           # the config used in 'dockers/ci-runner-ipu/Dockerfile'
           - {python_version: "3.9", pytorch_version: "1.9"}
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - uses: docker/setup-buildx-action@v2
-      - uses: docker/login-action@v1
+      - uses: docker/login-action@v2
         if: env.PUSH_TO_HUB == 'true'
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
-      - uses: docker/build-push-action@v2
+      - uses: docker/build-push-action@v3
         with:
           build-args: |
             PYTHON_VERSION=${{ matrix.python_version }}
@@ -184,7 +207,7 @@ jobs:
           push: ${{ env.PUSH_TO_HUB }}
           tags: pytorchlightning/pytorch_lightning:base-ipu-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }}
         timeout-minutes: 100
-      - uses: docker/build-push-action@v2
+      - uses: docker/build-push-action@v3
         with:
           build-args: |
             PYTHON_VERSION=${{ matrix.python_version }}
@@ -199,7 +222,7 @@ jobs:
           status: ${{ job.status }}
           token: ${{ secrets.GITHUB_TOKEN }}
           notification_title: ${{ format('IPU; {0} py{1} for *{2}*', runner.os, matrix.python_version, matrix.pytorch_version) }}
-          message_format: '{emoji} *{workflow}* {status_message}, see <{run_url}|detail>, cc: <@U01BULUS2BG>'  # SeanNaren
+          message_format: '{emoji} *{workflow}* {status_message}, see <{run_url}|detail>, cc: <@@U01A5T7EY9M>'  # akihironitta
         env:
           SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
 
@@ -212,14 +235,14 @@ jobs:
           # the config used in 'dockers/ci-runner-hpu/Dockerfile'
           - {gaudi_version: "1.5.0", pytorch_version: "1.11.0"}
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - uses: docker/setup-buildx-action@v2
-      - uses: docker/login-action@v1
+      - uses: docker/login-action@v2
         if: env.PUSH_TO_HUB == 'true'
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
-      - uses: docker/build-push-action@v2
+      - uses: docker/build-push-action@v3
         with:
           build-args: |
             DIST=latest
@@ -243,10 +266,10 @@ jobs:
     runs-on: ubuntu-20.04
     steps:
       - name: Checkout
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
       - name: Build Conda Docker
         # publish master/release
-        uses: docker/build-push-action@v2
+        uses: docker/build-push-action@v3
         with:
           file: dockers/nvidia/Dockerfile
           push: false

.github/workflows/release-docker.yml

@@ -1,6 +1,5 @@
 name: Docker
-# https://www.docker.com/blog/first-docker-github-action-is-here
-# https://github.com/docker/build-push-action
+
 on:
   push:
     branches: [master, "release/*"]
@@ -15,8 +14,22 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python_version: ["3.7", "3.8", "3.9"]
-        pytorch_version: ["1.9", "1.10"]
+        include:
+          # Include all Python and PyTorch versions that PL supports.
+          - {python_version: "3.7", pytorch_version: "1.9", cuda_version: "11.1.1"}
+          - {python_version: "3.7", pytorch_version: "1.10", cuda_version: "11.3.1"}
+          - {python_version: "3.7", pytorch_version: "1.11", cuda_version: "11.3.1"}
+          - {python_version: "3.7", pytorch_version: "1.12", cuda_version: "11.3.1"}
+          - {python_version: "3.8", pytorch_version: "1.9", cuda_version: "11.1.1"}
+          - {python_version: "3.8", pytorch_version: "1.10", cuda_version: "11.3.1"}
+          - {python_version: "3.8", pytorch_version: "1.11", cuda_version: "11.3.1"}
+          - {python_version: "3.8", pytorch_version: "1.12", cuda_version: "11.3.1"}
+          - {python_version: "3.9", pytorch_version: "1.9", cuda_version: "11.1.1"}
+          - {python_version: "3.9", pytorch_version: "1.10", cuda_version: "11.3.1"}
+          - {python_version: "3.9", pytorch_version: "1.11", cuda_version: "11.3.1"}
+          - {python_version: "3.9", pytorch_version: "1.12", cuda_version: "11.3.1"}
+          # - {python_version: "3.10", pytorch_version: "1.11", cuda_version: "11.3.1"}
+          # - {python_version: "3.10", pytorch_version: "1.12", cuda_version: "11.3.1"}
     steps:
       - name: Checkout
         uses: actions/checkout@v2
@@ -32,19 +45,29 @@ jobs:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
           dockerfile: dockers/release/Dockerfile
-          build_args: PYTHON_VERSION=${{ matrix.python_version }},PYTORCH_VERSION=${{ matrix.pytorch_version }},LIGHTNING_VERSION=${{ steps.get_version.outputs.RELEASE_VERSION }}
-          tags: "${{ steps.get_version.outputs.RELEASE_VERSION }}-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }},latest-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }}"
+          build_args: |
+            PYTHON_VERSION=${{ matrix.python_version }}
+            PYTORCH_VERSION=${{ matrix.pytorch_version }}
+            CUDA_VERSION=${{ matrix.cuda_version }}
+            LIGHTNING_VERSION=${{ steps.get_version.outputs.RELEASE_VERSION }}
+          tags: |
+            ${{ steps.get_version.outputs.RELEASE_VERSION }}-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }}-cuda${{ matrix.cuda_version }}
+            latest-py${{ matrix.python_version }}-torch${{ matrix.pytorch_version }}-cuda${{ matrix.cuda_version }}
         timeout-minutes: 55
 
       - name: Publish Latest to Docker
         uses: docker/build-push-action@v1.1.0
-        # only on releases and latest Python and PyTorch
-        if: matrix.python_version == '3.9' && matrix.pytorch_version == '1.10'
+        # Only latest Python and PyTorch
+        if: matrix.python_version == '3.9' && matrix.pytorch_version == '1.11'
         with:
           repository: pytorchlightning/pytorch_lightning
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
           dockerfile: dockers/release/Dockerfile
-          build_args: PYTHON_VERSION=${{ matrix.python_version }},PYTORCH_VERSION=${{ matrix.pytorch_version }},LIGHTNING_VERSION=${{ steps.get_version.outputs.RELEASE_VERSION }}
+          build_args: |
+            PYTHON_VERSION=${{ matrix.python_version }}
+            PYTORCH_VERSION=${{ matrix.pytorch_version }}
+            CUDA_VERSION=${{ matrix.cuda_version }}
+            LIGHTNING_VERSION=${{ steps.get_version.outputs.RELEASE_VERSION }}
           tags: "latest"
         timeout-minutes: 55