Merge branch 'master' into stepwiseLRscheduler

Author: lantiga

.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"

.azure/gpu-tests-fabric.yml

@@ -107,7 +107,7 @@ jobs:
       - bash: |
           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 setuptools==75.6.0 jsonargparse==4.35.0
         displayName: "Install package & dependencies"
 
       - bash: |

.azure/gpu-tests-pytorch.yml

@@ -111,7 +111,7 @@ jobs:
       - bash: |
           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 setuptools==75.6.0 jsonargparse==4.35.0
         displayName: "Install package & dependencies"
 
       - bash: pip uninstall -y lightning

.github/CONTRIBUTING.md

@@ -182,7 +182,7 @@ 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
 

.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/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

@@ -23,26 +23,26 @@ subprojects:
       - "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 (macOS-14, lightning, 3.12.7, 2.4.1)"
+      - "pl-cpu (macOS-14, lightning, 3.12.7, 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 (ubuntu-22.04, lightning, 3.12.7, 2.4.1)"
+      - "pl-cpu (ubuntu-22.04, lightning, 3.12.7, 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 (windows-2022, lightning, 3.12.7, 2.4.1)"
+      - "pl-cpu (windows-2022, lightning, 3.12.7, 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 (macOS-14, pytorch, 3.12.7, 2.5.1)"
+      - "pl-cpu (ubuntu-22.04, pytorch, 3.12.7, 2.5.1)"
+      - "pl-cpu (windows-2022, pytorch, 3.12.7, 2.5.1)"
 
   - id: "pytorch_lightning: Azure GPU"
     paths:
@@ -145,17 +145,17 @@ 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-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, true)"
 
   # SECTION: lightning_fabric
 
@@ -176,26 +176,26 @@ subprojects:
       - "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 (macOS-14, lightning, 3.12.7, 2.4.1)"
+      - "fabric-cpu (macOS-14, lightning, 3.12.7, 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 (ubuntu-22.04, lightning, 3.12.7, 2.4.1)"
+      - "fabric-cpu (ubuntu-22.04, lightning, 3.12.7, 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 (windows-2022, lightning, 3.12.7, 2.4.1)"
+      - "fabric-cpu (windows-2022, lightning, 3.12.7, 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 (macOS-14, fabric, 3.12.7, 2.5.1)"
+      - "fabric-cpu (ubuntu-22.04, fabric, 3.12.7, 2.5.1)"
+      - "fabric-cpu (windows-2022, fabric, 3.12.7, 2.5.1)"
 
   - id: "lightning_fabric: Azure GPU"
     paths:

.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.