Minor path release 2.5.1 [rebase & merge]

.azure/gpu-benchmarks.yml

@@ -108,5 +108,6 @@ jobs:
         condition: and(succeeded(), eq(variables['PACKAGE_NAME'], 'fabric'))
         env:
           PL_RUN_CUDA_TESTS: "1"
+          PL_RUN_STANDALONE_TESTS: "1"
         displayName: "Testing: fabric standalone tasks"
         timeoutInMinutes: "10"

.azure/gpu-tests-fabric.yml

@@ -56,11 +56,14 @@ jobs:
       options: "--gpus=all --shm-size=2gb  -v /var/tmp:/var/tmp"
     strategy:
       matrix:
+        "Fabric | oldest":
+          image: "pytorchlightning/pytorch_lightning:base-cuda-py3.10-torch2.1-cuda12.1.1"
+          PACKAGE_NAME: "fabric"
         "Fabric | latest":
-          image: "pytorchlightning/pytorch_lightning:base-cuda-py3.11-torch2.3-cuda12.1.0"
+          image: "pytorchlightning/pytorch_lightning:base-cuda-py3.12-torch2.6-cuda12.4.1"
           PACKAGE_NAME: "fabric"
         "Lightning | latest":
-          image: "pytorchlightning/pytorch_lightning:base-cuda-py3.12-torch2.5-cuda12.1.0"
+          image: "pytorchlightning/pytorch_lightning:base-cuda-py3.12-torch2.6-cuda12.4.1"
           PACKAGE_NAME: "lightning"
     workspace:
       clean: all
@@ -77,9 +80,8 @@ jobs:
         displayName: "set env. vars"
       - bash: |
           echo "##vso[task.setvariable variable=TORCH_URL]https://download.pytorch.org/whl/test/cu${CUDA_VERSION_MM}"
-          echo "##vso[task.setvariable variable=TORCHVISION_URL]https://download.pytorch.org/whl/test/cu124/torchvision-0.19.0%2Bcu124-cp${PYTHON_VERSION_MM}-cp${PYTHON_VERSION_MM}-linux_x86_64.whl"
         condition: endsWith(variables['Agent.JobName'], 'future')
-        displayName: "set env. vars 4 future"
+        displayName: "extend env. vars 4 future"
 
       - bash: |
           echo $(DEVICES)
@@ -105,15 +107,17 @@ jobs:
         displayName: "Adjust dependencies"
 
       - bash: |
+          set -e
           extra=$(python -c "print({'lightning': 'fabric-'}.get('$(PACKAGE_NAME)', ''))")
-          pip install -e ".[${extra}dev]" pytest-timeout -U --find-links="${TORCH_URL}" --find-links="${TORCHVISION_URL}"
+          pip install -e ".[${extra}dev]" pytest-timeout -U --extra-index-url="${TORCH_URL}"
           pip install setuptools==75.6.0 jsonargparse==4.35.0
         displayName: "Install package & dependencies"
 
       - bash: |
           set -e
           python requirements/collect_env_details.py
           python -c "import torch ; mgpu = torch.cuda.device_count() ; assert mgpu == 2, f'GPU: {mgpu}'"
+          python requirements/pytorch/check-avail-extras.py
           python -c "import bitsandbytes"
         displayName: "Env details"
 
@@ -140,10 +144,12 @@ jobs:
         displayName: "Testing: fabric standard"
         timeoutInMinutes: "10"
 
-      - bash: bash ./run_standalone_tests.sh "tests_fabric"
+      - bash: |
+          wget https://raw.githubusercontent.com/Lightning-AI/utilities/main/scripts/run_standalone_tests.sh
+          bash ./run_standalone_tests.sh "tests_fabric"
         workingDirectory: tests/
         env:
-          PL_STANDALONE_TESTS_SOURCE: $(COVERAGE_SOURCE)
+          PL_RUN_STANDALONE_TESTS: "1"
         displayName: "Testing: fabric standalone"
         timeoutInMinutes: "10"
 

.azure/gpu-tests-pytorch.yml

@@ -49,11 +49,14 @@ jobs:
     cancelTimeoutInMinutes: "2"
     strategy:
       matrix:
+        "PyTorch | oldest":
+          image: "pytorchlightning/pytorch_lightning:base-cuda-py3.10-torch2.1-cuda12.1.1"
+          PACKAGE_NAME: "pytorch"
         "PyTorch | latest":
-          image: "pytorchlightning/pytorch_lightning:base-cuda-py3.11-torch2.3-cuda12.1.0"
+          image: "pytorchlightning/pytorch_lightning:base-cuda-py3.12-torch2.6-cuda12.4.1"
           PACKAGE_NAME: "pytorch"
         "Lightning | latest":
-          image: "pytorchlightning/pytorch_lightning:base-cuda-py3.12-torch2.5-cuda12.1.0"
+          image: "pytorchlightning/pytorch_lightning:base-cuda-py3.12-torch2.6-cuda12.4.1"
           PACKAGE_NAME: "lightning"
     pool: lit-rtx-3090
     variables:
@@ -81,9 +84,8 @@ jobs:
         displayName: "set env. vars"
       - bash: |
           echo "##vso[task.setvariable variable=TORCH_URL]https://download.pytorch.org/whl/test/cu${CUDA_VERSION_MM}"
-          echo "##vso[task.setvariable variable=TORCHVISION_URL]https://download.pytorch.org/whl/test/cu124/torchvision-0.19.0%2Bcu124-cp${PYTHON_VERSION_MM}-cp${PYTHON_VERSION_MM}-linux_x86_64.whl"
         condition: endsWith(variables['Agent.JobName'], 'future')
-        displayName: "set env. vars 4 future"
+        displayName: "extend env. vars 4 future"
 
       - bash: |
           echo $(DEVICES)
@@ -109,8 +111,9 @@ jobs:
         displayName: "Adjust dependencies"
 
       - bash: |
+          set -e
           extra=$(python -c "print({'lightning': 'pytorch-'}.get('$(PACKAGE_NAME)', ''))")
-          pip install -e ".[${extra}dev]" pytest-timeout -U --find-links="${TORCH_URL}" --find-links="${TORCHVISION_URL}"
+          pip install -e ".[${extra}dev]" pytest-timeout -U --extra-index-url="${TORCH_URL}"
           pip install setuptools==75.6.0 jsonargparse==4.35.0
         displayName: "Install package & dependencies"
 
@@ -161,11 +164,13 @@ jobs:
         displayName: "Testing: PyTorch standard"
         timeoutInMinutes: "35"
 
-      - bash: bash ./run_standalone_tests.sh "tests_pytorch"
+      - bash: |
+          wget https://raw.githubusercontent.com/Lightning-AI/utilities/main/scripts/run_standalone_tests.sh
+          bash ./run_standalone_tests.sh "tests_pytorch"
         workingDirectory: tests/
         env:
           PL_USE_MOCKED_MNIST: "1"
-          PL_STANDALONE_TESTS_SOURCE: $(COVERAGE_SOURCE)
+          PL_RUN_STANDALONE_TESTS: "1"
         displayName: "Testing: PyTorch standalone tests"
         timeoutInMinutes: "35"
 

.github/CONTRIBUTING.md

@@ -182,14 +182,14 @@ We welcome any useful contribution! For your convenience here's a recommended wo
 1. Use tags in PR name for the following cases:
 
    - **\[blocked by #<number>\]** if your work is dependent on other PRs.
-   - **\[wip\]** when you start to re-edit your work, mark it so no one will accidentally merge it in meantime.
+   - **[wip]** when you start to re-edit your work, mark it so no one will accidentally merge it in meantime.
 
 ### Question & Answer
 
 #### How can I help/contribute?
 
 All types of contributions are welcome - reporting bugs, fixing documentation, adding test cases, solving issues, and preparing bug fixes.
-To get started with code contributions, look for issues marked with the label [good first issue](https://github.com/Lightning-AI/lightning/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22) or chose something close to your domain with the label [help wanted](https://github.com/Lightning-AI/lightning/issues?q=is%3Aopen+is%3Aissue+label%3A%22help+wanted%22). Before coding, make sure that the issue description is clear and comment on the issue so that we can assign it to you (or simply self-assign if you can).
+To get started with code contributions, look for issues marked with the label [good first issue](https://github.com/Lightning-AI/pytorch-lightning/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22) or chose something close to your domain with the label [help wanted](https://github.com/Lightning-AI/pytorch-lightning/issues?q=is%3Aopen+is%3Aissue+label%3A%22help+wanted%22). Before coding, make sure that the issue description is clear and comment on the issue so that we can assign it to you (or simply self-assign if you can).
 
 #### Is there a recommendation for branch names?
 

.github/actions/pip-wheels/action.yml

@@ -46,8 +46,8 @@ runs:
       run: |
         # cat requirements.dump
         pip wheel -r requirements.dump --prefer-binary \
-          --wheel-dir=.wheels \
-          -f ${{ inputs.torch-url }} -f ${{ inputs.wheel-dir }}
+          --wheel-dir=".wheels" \
+          --extra-index-url=${{ inputs.torch-url }} -f ${{ inputs.wheel-dir }}
         ls -lh .wheels/
       shell: bash
 

.github/checkgroup.yml

@@ -19,30 +19,7 @@ subprojects:
       - "!*.md"
       - "!**/*.md"
     checks:
-      - "pl-cpu (macOS-14, lightning, 3.9, 2.1, oldest)"
-      - "pl-cpu (macOS-14, lightning, 3.10, 2.1)"
-      - "pl-cpu (macOS-14, lightning, 3.11, 2.2.2)"
-      - "pl-cpu (macOS-14, lightning, 3.11, 2.3)"
-      - "pl-cpu (macOS-14, lightning, 3.12, 2.4.1)"
-      - "pl-cpu (macOS-14, lightning, 3.12, 2.5.1)"
-      - "pl-cpu (ubuntu-20.04, lightning, 3.9, 2.1, oldest)"
-      - "pl-cpu (ubuntu-20.04, lightning, 3.10, 2.1)"
-      - "pl-cpu (ubuntu-20.04, lightning, 3.11, 2.2.2)"
-      - "pl-cpu (ubuntu-20.04, lightning, 3.11, 2.3)"
-      - "pl-cpu (ubuntu-22.04, lightning, 3.12, 2.4.1)"
-      - "pl-cpu (ubuntu-22.04, lightning, 3.12, 2.5.1)"
-      - "pl-cpu (windows-2022, lightning, 3.9, 2.1, oldest)"
-      - "pl-cpu (windows-2022, lightning, 3.10, 2.1)"
-      - "pl-cpu (windows-2022, lightning, 3.11, 2.2.2)"
-      - "pl-cpu (windows-2022, lightning, 3.11, 2.3)"
-      - "pl-cpu (windows-2022, lightning, 3.12, 2.4.1)"
-      - "pl-cpu (windows-2022, lightning, 3.12, 2.5.1)"
-      - "pl-cpu (macOS-14, pytorch, 3.9, 2.1)"
-      - "pl-cpu (ubuntu-20.04, pytorch, 3.9, 2.1)"
-      - "pl-cpu (windows-2022, pytorch, 3.9, 2.1)"
-      - "pl-cpu (macOS-14, pytorch, 3.12, 2.5.1)"
-      - "pl-cpu (ubuntu-22.04, pytorch, 3.12, 2.5.1)"
-      - "pl-cpu (windows-2022, pytorch, 3.12, 2.5.1)"
+      - "pl-cpu-guardian" # aggregated check for all cases
 
   - id: "pytorch_lightning: Azure GPU"
     paths:
@@ -172,30 +149,7 @@ subprojects:
       - "!*.md"
       - "!**/*.md"
     checks:
-      - "fabric-cpu (macOS-14, lightning, 3.9, 2.1, oldest)"
-      - "fabric-cpu (macOS-14, lightning, 3.10, 2.1)"
-      - "fabric-cpu (macOS-14, lightning, 3.11, 2.2.2)"
-      - "fabric-cpu (macOS-14, lightning, 3.11, 2.3)"
-      - "fabric-cpu (macOS-14, lightning, 3.12, 2.4.1)"
-      - "fabric-cpu (macOS-14, lightning, 3.12, 2.5.1)"
-      - "fabric-cpu (ubuntu-20.04, lightning, 3.9, 2.1, oldest)"
-      - "fabric-cpu (ubuntu-20.04, lightning, 3.10, 2.1)"
-      - "fabric-cpu (ubuntu-20.04, lightning, 3.11, 2.2.2)"
-      - "fabric-cpu (ubuntu-20.04, lightning, 3.11, 2.3)"
-      - "fabric-cpu (ubuntu-22.04, lightning, 3.12, 2.4.1)"
-      - "fabric-cpu (ubuntu-22.04, lightning, 3.12, 2.5.1)"
-      - "fabric-cpu (windows-2022, lightning, 3.9, 2.1, oldest)"
-      - "fabric-cpu (windows-2022, lightning, 3.10, 2.1)"
-      - "fabric-cpu (windows-2022, lightning, 3.11, 2.2.2)"
-      - "fabric-cpu (windows-2022, lightning, 3.11, 2.3)"
-      - "fabric-cpu (windows-2022, lightning, 3.12, 2.4.1)"
-      - "fabric-cpu (windows-2022, lightning, 3.12, 2.5.1)"
-      - "fabric-cpu (macOS-14, fabric, 3.9, 2.1)"
-      - "fabric-cpu (ubuntu-20.04, fabric, 3.9, 2.1)"
-      - "fabric-cpu (windows-2022, fabric, 3.9, 2.1)"
-      - "fabric-cpu (macOS-14, fabric, 3.12, 2.5.1)"
-      - "fabric-cpu (ubuntu-22.04, fabric, 3.12, 2.5.1)"
-      - "fabric-cpu (windows-2022, fabric, 3.12, 2.5.1)"
+      - "fabric-cpu-guardian" # aggregated check for all cases
 
   - id: "lightning_fabric: Azure GPU"
     paths:
@@ -259,27 +213,4 @@ subprojects:
       - "!*.md"
       - "!**/*.md"
     checks:
-      - "install-pkg (ubuntu-22.04, fabric, 3.9)"
-      - "install-pkg (ubuntu-22.04, fabric, 3.11)"
-      - "install-pkg (ubuntu-22.04, pytorch, 3.9)"
-      - "install-pkg (ubuntu-22.04, pytorch, 3.11)"
-      - "install-pkg (ubuntu-22.04, lightning, 3.9)"
-      - "install-pkg (ubuntu-22.04, lightning, 3.11)"
-      - "install-pkg (ubuntu-22.04, notset, 3.9)"
-      - "install-pkg (ubuntu-22.04, notset, 3.11)"
-      - "install-pkg (macOS-14, fabric, 3.9)"
-      - "install-pkg (macOS-14, fabric, 3.11)"
-      - "install-pkg (macOS-14, pytorch, 3.9)"
-      - "install-pkg (macOS-14, pytorch, 3.11)"
-      - "install-pkg (macOS-14, lightning, 3.9)"
-      - "install-pkg (macOS-14, lightning, 3.11)"
-      - "install-pkg (macOS-14, notset, 3.9)"
-      - "install-pkg (macOS-14, notset, 3.11)"
-      - "install-pkg (windows-2022, fabric, 3.9)"
-      - "install-pkg (windows-2022, fabric, 3.11)"
-      - "install-pkg (windows-2022, pytorch, 3.9)"
-      - "install-pkg (windows-2022, pytorch, 3.11)"
-      - "install-pkg (windows-2022, lightning, 3.9)"
-      - "install-pkg (windows-2022, lightning, 3.11)"
-      - "install-pkg (windows-2022, notset, 3.9)"
-      - "install-pkg (windows-2022, notset, 3.11)"
+      - "install-pkg-guardian" # aggregated check for all cases

.github/workflows/README.md

@@ -16,7 +16,7 @@ Brief description of all our automation tools used for boosting development perf
 | .azure-pipelines/gpu-benchmarks.yml    | Run speed/memory benchmarks for parity with vanila PyTorch.                               | GPU         |
 | .github/workflows/ci-flagship-apps.yml | Run end-2-end tests with full applications, including deployment to the production cloud. | CPU         |
 | .github/workflows/ci-tests-pytorch.yml | Run all tests except for accelerator-specific, standalone and slow tests.                 | CPU         |
-| .github/workflows/tpu-tests.yml        | Run only TPU-specific tests. Requires that the PR title contains '\[TPU\]'                | TPU         |
+| .github/workflows/tpu-tests.yml        | Run only TPU-specific tests. Requires that the PR title contains '[TPU]'                  | TPU         |
 
 \* Each standalone test needs to be run in separate processes to avoid unwanted interactions between test cases.
 

.github/workflows/_legacy-checkpoints.yml

@@ -43,7 +43,7 @@ on:
 
 env:
   LEGACY_FOLDER: "tests/legacy"
-  TORCH_URL: "https://download.pytorch.org/whl/cpu/torch_stable.html"
+  TORCH_URL: "https://download.pytorch.org/whl/cpu/"
 
 defaults:
   run:
@@ -67,12 +67,12 @@ jobs:
           PACKAGE_NAME: pytorch
           FREEZE_REQUIREMENTS: 1
         timeout-minutes: 20
-        run: pip install . -f ${TORCH_URL}
+        run: pip install . --extra-index-url="${TORCH_URL}"
         if: inputs.pl_version == ''
 
       - name: Install PL version
         timeout-minutes: 20
-        run: pip install "pytorch-lightning==${{ inputs.pl_version }}" -f ${TORCH_URL}
+        run: pip install "pytorch-lightning==${{ inputs.pl_version }}" --extra-index-url="${TORCH_URL}"
         if: inputs.pl_version != ''
 
       - name: Adjust tests -> PL

.github/workflows/call-clear-cache.yml

@@ -23,18 +23,18 @@ on:
 jobs:
   cron-clear:
     if: github.event_name == 'schedule' || github.event_name == 'pull_request'
-    uses: Lightning-AI/utilities/.github/workflows/cleanup-caches.yml@v0.11.9
+    uses: Lightning-AI/utilities/.github/workflows/cleanup-caches.yml@v0.14.1
     with:
-      scripts-ref: v0.11.8
+      scripts-ref: v0.14.1
       dry-run: ${{ github.event_name == 'pull_request' }}
       pattern: "latest|docs"
       age-days: 7
 
   direct-clear:
     if: github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request'
-    uses: Lightning-AI/utilities/.github/workflows/cleanup-caches.yml@v0.11.9
+    uses: Lightning-AI/utilities/.github/workflows/cleanup-caches.yml@v0.14.1
     with:
-      scripts-ref: v0.11.8
+      scripts-ref: v0.14.1
       dry-run: ${{ github.event_name == 'pull_request' }}
       pattern: ${{ inputs.pattern || 'pypi_wheels' }} # setting str in case of PR / debugging
       age-days: ${{ fromJSON(inputs.age-days) || 0 }} # setting 0 in case of PR / debugging

.github/workflows/ci-check-md-links.yml

@@ -14,7 +14,7 @@ on:
 
 jobs:
   check-md-links:
-    uses: Lightning-AI/utilities/.github/workflows/check-md-links.yml@v0.11.9
+    uses: Lightning-AI/utilities/.github/workflows/check-md-links.yml@v0.14.1
     with:
       config-file: ".github/markdown-links-config.json"
       base-branch: "master"

.github/workflows/ci-pkg-install.yml

@@ -103,3 +103,17 @@ jobs:
           LIGHTING_TESTING: 1 # path for require wrapper
           PY_IGNORE_IMPORTMISMATCH: 1
         run: python -m pytest src/lit/${PKG_NAME} --ignore-glob="**/cli/*-template/**" --doctest-plus
+
+  install-pkg-guardian:
+    runs-on: ubuntu-latest
+    needs: install-pkg
+    if: always()
+    steps:
+      - run: echo "${{ needs.install-pkg.result }}"
+      - name: failing...
+        if: needs.install-pkg.result == 'failure'
+        run: exit 1
+      - name: cancelled or skipped...
+        if: contains(fromJSON('["cancelled", "skipped"]'), needs.install-pkg.result)
+        timeout-minutes: 1
+        run: sleep 90

.github/workflows/ci-schema.yml

@@ -8,7 +8,7 @@ on:
 
 jobs:
   check:
-    uses: Lightning-AI/utilities/.github/workflows/check-schema.yml@v0.11.9
+    uses: Lightning-AI/utilities/.github/workflows/check-schema.yml@v0.14.1
     with:
       # skip azure due to the wrong schema file by MSFT
       # https://github.com/Lightning-AI/lightning-flash/pull/1455#issuecomment-1244793607