Merge branch 'master' into chualan/fix-19658

Author: Borda

.actions/assistant.py

@@ -481,23 +481,27 @@ def convert_version2nightly(ver_file: str = "src/version.info") -> None:
         with open(ver_file, "w") as fo:
             fo.write(version + os.linesep)
 
+    @staticmethod
+    def generate_docker_tags(
+        release_version: str,
+        python_version: str,
+        torch_version: str,
+        cuda_version: str,
+        docker_project: str = "pytorchlightning/pytorch_lightning",
+        add_latest: bool = False,
+    ) -> None:
+        """Generate docker tags for the given versions."""
+        tags = [f"latest-py{python_version}-torch{torch_version}-cuda{cuda_version}"]
+        if release_version:
+            tags += [f"{release_version}-py{python_version}-torch{torch_version}-cuda{cuda_version}"]
+        if add_latest:
+            tags += ["latest"]
 
-if __name__ == "__main__":
-    import sys
-
-    import jsonargparse
-    from jsonargparse import ArgumentParser
-
-    def patch_jsonargparse_python_3_12_8():
-        if sys.version_info < (3, 12, 8):
-            return
-
-        def _parse_known_args_patch(self: ArgumentParser, args: Any = None, namespace: Any = None) -> tuple[Any, Any]:
-            namespace, args = super(ArgumentParser, self)._parse_known_args(args, namespace, intermixed=False)  # type: ignore
-            return namespace, args
+        tags = [f"{docker_project}:{tag}" for tag in tags]
+        print(",".join(tags))
 
-        setattr(ArgumentParser, "_parse_known_args", _parse_known_args_patch)
 
-    patch_jsonargparse_python_3_12_8()  # Required until fix https://github.com/omni-us/jsonargparse/issues/641
+if __name__ == "__main__":
+    import jsonargparse
 
     jsonargparse.CLI(AssistantCLI, as_positional=False)

.actions/requirements.txt

@@ -1,3 +1,3 @@
-jsonargparse >=4.16.0, <4.28.0
+jsonargparse >=4.16.0, <=4.35.0
 requests
 packaging

.azure/gpu-benchmarks.yml

@@ -77,7 +77,7 @@ jobs:
 
       - bash: |
           pip install -e .[dev] --find-links ${TORCH_URL}
-          pip install setuptools==75.6.0
+          pip install setuptools==75.6.0 jsonargparse==4.35.0
         env:
           FREEZE_REQUIREMENTS: "1"
         displayName: "Install package"
@@ -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 +56,17 @@ 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"
+        "Fabric | future":
+          image: "pytorchlightning/pytorch_lightning:base-cuda-py3.12-torch2.7-cuda12.6.3"
           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 +83,8 @@ 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 +110,17 @@ 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="${TORCHVISION_URL}"
-          pip install setuptools==75.6.0
+          pip install -e ".[${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 +147,12 @@ 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 +49,17 @@ 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"
+        "PyTorch | future":
+          image: "pytorchlightning/pytorch_lightning:base-cuda-py3.12-torch2.7-cuda12.6.3"
           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 +87,8 @@ 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)
@@ -109,9 +114,10 @@ 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="${TORCHVISION_URL}"
-          pip install setuptools==75.6.0
+          pip install -e ".[${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: pip uninstall -y lightning
@@ -161,11 +167,13 @@ 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/ISSUE_TEMPLATE/1_bug_report.yaml

@@ -37,6 +37,7 @@ body:
         - "v2.2"
         - "v2.3"
         - "v2.4"
+        - "v2.5"
         - "master"
     validations:
       required: true
@@ -91,8 +92,8 @@ body:
           <summary>Current environment</summary>
 
         ```
-        #- PyTorch Lightning Version (e.g., 2.4.0):
-        #- PyTorch Version (e.g., 2.4):
+        #- PyTorch Lightning Version (e.g., 2.5.0):
+        #- PyTorch Version (e.g., 2.5):
         #- Python version (e.g., 3.12):
         #- OS (e.g., Linux):
         #- CUDA/cuDNN version:

.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/advanced-issue-labeler.yml

@@ -16,5 +16,7 @@ policy:
             keys: ["v2_3", "v2.3", "2.3.x"]
           - name: "ver: 2.4.x"
             keys: ["v2_4", "v2.4", "2.4.x"]
-          - name: "ver: 2.4.x"
+          - name: "ver: 2.5.x"
+            keys: ["v2_5", "v2.5", "2.5.x"]
+          - name: "ver: 2.5.x"
             keys: ["master"]

.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:
@@ -145,17 +122,19 @@ subprojects:
       - "!*.md"
       - "!**/*.md"
     checks:
-      - "build-cuda (3.10, 2.1.2, 12.1.0)"
-      - "build-cuda (3.11, 2.2.2, 12.1.0)"
-      - "build-cuda (3.11, 2.3.1, 12.1.0)"
-      - "build-cuda (3.11, 2.4.1, 12.1.0)"
-      - "build-cuda (3.12, 2.5.1, 12.1.0)"
+      - "build-cuda (3.10, 2.1.2, 12.1.1)"
+      - "build-cuda (3.11, 2.2.2, 12.1.1)"
+      - "build-cuda (3.11, 2.3.1, 12.1.1)"
+      - "build-cuda (3.11, 2.4.1, 12.1.1)"
+      - "build-cuda (3.12, 2.5.1, 12.1.1)"
+      - "build-cuda (3.12, 2.6.0, 12.4.1)"
       #- "build-NGC"
-      - "build-pl (3.10, 2.1, 12.1.0)"
-      - "build-pl (3.11, 2.2, 12.1.0)"
-      - "build-pl (3.11, 2.3, 12.1.0)"
-      - "build-pl (3.11, 2.4, 12.1.0)"
-      - "build-pl (3.12, 2.5, 12.1.0)"
+      - "build-pl (3.10, 2.1, 12.1.1)"
+      - "build-pl (3.11, 2.2, 12.1.1)"
+      - "build-pl (3.11, 2.3, 12.1.1)"
+      - "build-pl (3.11, 2.4, 12.1.1)"
+      - "build-pl (3.12, 2.5, 12.1.1)"
+      - "build-pl (3.12, 2.6, 12.4.1, true)"
 
   # SECTION: lightning_fabric
 
@@ -172,30 +151,7 @@ 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 +215,4 @@ 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