Merge branch 'master' into feat/ModelCheckpointException

Borda · web-flow · commit 033647871532 · 2025-08-08T19:21:37.000+03:00
diff --git a/.github/CONTRIBUTING.md b/.github/CONTRIBUTING.md
@@ -113,14 +113,28 @@ ______________________________________________________________________
 
 To set up a local development environment, we recommend using `uv`, which can be installed following their [instructions](https://docs.astral.sh/uv/getting-started/installation/).
 
-Once `uv` has been installed, begin by cloning the repository:
+Once `uv` has been installed, begin by cloning the forked repository:
 
 ```bash
-git clone https://github.com/Lightning-AI/lightning.git
-cd lightning
+git clone https://github.com/{YOUR_GITHUB_USERNAME}/pytorch-lightning.git
+cd pytorch-lightning
 ```
 
-Once in root level of the repository, create a new virtual environment and install the project dependencies.
+> If you're using [Lightning Studio](https://lightning.ai) or already have your `uv venv` activated, you can quickly set up the project by running:
+
+```bash
+make setup
+```
+
+This will:
+
+- Install all required dependencies.
+- Perform an editable install of the `pytorch-lightning` project.
+- Install and configure `pre-commit`.
+
+#### Manual Setup (Optional)
+
+If you prefer more fine-grained control over the dependencies, you can set up the environment manually:
 
 ```bash
 uv venv
diff --git a/.github/checkgroup.yml b/.github/checkgroup.yml
@@ -135,7 +135,8 @@ subprojects:
       - "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)"
-      - "build-pl (3.12, 2.7, 12.6.3, true)"
+      - "build-pl (3.12, 2.7, 12.6.3)"
+      - "build-pl (3.12, 2.8, 12.6.3, true)"
 
   # SECTION: lightning_fabric
 
diff --git a/.github/workflows/call-clear-cache.yml b/.github/workflows/call-clear-cache.yml
@@ -23,7 +23,7 @@ on:
 jobs:
   cron-clear:
     if: github.event_name == 'schedule' || github.event_name == 'pull_request'
-    uses: Lightning-AI/utilities/.github/workflows/cleanup-caches.yml@v0.14.3
+    uses: Lightning-AI/utilities/.github/workflows/cleanup-caches.yml@v0.15.0
     with:
       scripts-ref: v0.14.3
       dry-run: ${{ github.event_name == 'pull_request' }}
@@ -32,7 +32,7 @@ jobs:
 
   direct-clear:
     if: github.event_name == 'workflow_dispatch' || github.event_name == 'pull_request'
-    uses: Lightning-AI/utilities/.github/workflows/cleanup-caches.yml@v0.14.3
+    uses: Lightning-AI/utilities/.github/workflows/cleanup-caches.yml@v0.15.0
     with:
       scripts-ref: v0.14.3
       dry-run: ${{ github.event_name == 'pull_request' }}
diff --git a/.github/workflows/ci-schema.yml b/.github/workflows/ci-schema.yml
@@ -8,7 +8,7 @@ on:
 
 jobs:
   check:
-    uses: Lightning-AI/utilities/.github/workflows/check-schema.yml@v0.14.3
+    uses: Lightning-AI/utilities/.github/workflows/check-schema.yml@v0.15.0
     with:
       # skip azure due to the wrong schema file by MSFT
       # https://github.com/Lightning-AI/lightning-flash/pull/1455#issuecomment-1244793607
diff --git a/.github/workflows/docker-build.yml b/.github/workflows/docker-build.yml
@@ -49,7 +49,8 @@ jobs:
           - { python_version: "3.11", pytorch_version: "2.4", cuda_version: "12.1.1" }
           - { python_version: "3.12", pytorch_version: "2.5", cuda_version: "12.1.1" }
           - { python_version: "3.12", pytorch_version: "2.6", cuda_version: "12.4.1" }
-          - { python_version: "3.12", pytorch_version: "2.7", cuda_version: "12.6.3", latest: "true" }
+          - { python_version: "3.12", pytorch_version: "2.7", cuda_version: "12.6.3" }
+          - { python_version: "3.12", pytorch_version: "2.8", cuda_version: "12.6.3", latest: "true" }
     steps:
       - uses: actions/checkout@v4
         with:
@@ -97,7 +98,7 @@ jobs:
         # adding dome more images as Thunder mainly using python 3.10,
         # and we need to support integrations as for example LitGPT
         python_version: ["3.10"]
-        pytorch_version: ["2.6.0", "2.7.1"]
+        pytorch_version: ["2.7.1", "2.8.0"]
         cuda_version: ["12.6.3"]
         include:
           # These are the base images for PL release docker images.
@@ -109,6 +110,7 @@ jobs:
           - { python_version: "3.12", pytorch_version: "2.5.1", cuda_version: "12.1.1" }
           - { python_version: "3.12", pytorch_version: "2.6.0", cuda_version: "12.4.1" }
           - { python_version: "3.12", pytorch_version: "2.7.1", cuda_version: "12.6.3" }
+          - { python_version: "3.12", pytorch_version: "2.8.0", cuda_version: "12.6.3" }
     steps:
       - uses: actions/checkout@v4
       - uses: docker/setup-buildx-action@v3
@@ -129,6 +131,7 @@ jobs:
             PYTHON_VERSION=${{ matrix.python_version }}
             PYTORCH_VERSION=${{ matrix.pytorch_version }}
             CUDA_VERSION=${{ matrix.cuda_version }}
+            MAKE_FLAGS="-j2"
           file: dockers/base-cuda/Dockerfile
           push: ${{ env.PUSH_NIGHTLY }}
           tags: "pytorchlightning/pytorch_lightning:base-cuda-py${{ matrix.python_version }}-torch${{ env.PT_VERSION }}-cuda${{ matrix.cuda_version }}"
@@ -157,6 +160,8 @@ jobs:
         continue-on-error: true
         uses: docker/build-push-action@v6
         with:
+          build-args: |
+            PYTORCH_VERSION="25.04"
           file: dockers/nvidia/Dockerfile
           push: false
         timeout-minutes: 55
diff --git a/Makefile b/Makefile
@@ -1,4 +1,4 @@
-.PHONY: test clean docs
+.PHONY: test clean docs setup
 
 # to imitate SLURM set only single node
 export SLURM_LOCALID=0
@@ -7,6 +7,23 @@ export SPHINX_MOCK_REQUIREMENTS=1
 # install only Lightning Trainer packages
 export PACKAGE_NAME=pytorch
 
+setup:
+	uv pip install -r requirements.txt \
+	    -r requirements/pytorch/base.txt \
+	    -r requirements/pytorch/test.txt \
+	    -r requirements/pytorch/extra.txt \
+	    -r requirements/pytorch/strategies.txt \
+	    -r requirements/fabric/base.txt \
+	    -r requirements/fabric/test.txt \
+	    -r requirements/fabric/strategies.txt \
+	    -r requirements/typing.txt \
+	    -e ".[all]" \
+	    pre-commit
+	pre-commit install
+	@echo "-----------------------------"
+	@echo "✅ Environment setup complete. Ready to Contribute ⚡️!"
+
+
 clean:
 	# clean all temp runs
 	rm -rf $(shell find . -name "mlruns")
diff --git a/dockers/base-cuda/Dockerfile b/dockers/base-cuda/Dockerfile
@@ -19,8 +19,9 @@ ARG CUDA_VERSION=11.7.1
 FROM nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
 
 ARG PYTHON_VERSION=3.10
-ARG PYTORCH_VERSION=2.1
+ARG PYTORCH_VERSION=2.8
 ARG MAX_ALLOWED_NCCL=2.22.3
+ARG MAKE_FLAGS="-j$(nproc)"
 
 SHELL ["/bin/bash", "-c"]
 # https://techoverflow.net/2019/05/18/how-to-fix-configuring-tzdata-interactive-input-when-building-docker-images/
@@ -30,8 +31,7 @@ ENV \
     PATH="$PATH:/root/.local/bin" \
     CUDA_TOOLKIT_ROOT_DIR="/usr/local/cuda" \
     MKL_THREADING_LAYER="GNU" \
-    # MAKEFLAGS="-j$(nproc)"
-    MAKEFLAGS="-j2"
+    MAKEFLAGS=${MAKE_FLAGS}
 
 RUN \
     CUDA_VERSION_MM=${CUDA_VERSION%.*} && \
diff --git a/dockers/nvidia/Dockerfile b/dockers/nvidia/Dockerfile
@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-ARG PYTORCH_VERSION=22.09
+ARG PYTORCH_VERSION=24.05
 
 # https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes
 FROM nvcr.io/nvidia/pytorch:${PYTORCH_VERSION}-py3
diff --git a/dockers/release/Dockerfile b/dockers/release/Dockerfile
@@ -13,8 +13,8 @@
 # limitations under the License.
 
 ARG PYTHON_VERSION=3.10
-ARG PYTORCH_VERSION=2.0
-ARG CUDA_VERSION=11.8.0
+ARG PYTORCH_VERSION=2.8
+ARG CUDA_VERSION=12.6.3
 
 FROM pytorchlightning/pytorch_lightning:base-cuda-py${PYTHON_VERSION}-torch${PYTORCH_VERSION}-cuda${CUDA_VERSION}
 
diff --git a/docs/source-pytorch/accelerators/accelerator_prepare.rst b/docs/source-pytorch/accelerators/accelerator_prepare.rst
@@ -78,7 +78,7 @@ Synchronize validation and test logging
 ***************************************
 
 When running in distributed mode, we have to ensure that the validation and test step logging calls are synchronized across processes.
-This is done by adding ``sync_dist=True`` to all ``self.log`` calls in the validation and test step.
+This is done by adding ``sync_dist=True`` to all ``self.log`` calls in the validation and test step. This will automatically average values across all processes.
 This ensures that each GPU worker has the same behaviour when tracking model checkpoints, which is important for later downstream tasks such as testing the best checkpoint across all workers.
 The ``sync_dist`` option can also be used in logging calls during the step methods, but be aware that this can lead to significant communication overhead and slow down your training.
 
diff --git a/docs/source-pytorch/advanced/speed.rst b/docs/source-pytorch/advanced/speed.rst
@@ -464,7 +464,7 @@ takes a great deal of care to be optimized for this.
 Clear Cache
 ===========
 
-Don't call :func:`torch.cuda.empty_cache` unnecessarily! Every time you call this, ALL your GPUs have to wait to sync.
+Don't call ``torch.cuda.empty_cache`` unnecessarily! Every time you call this, ALL your GPUs have to wait to sync.
 
 Transferring Tensors to Device
 ==============================
diff --git a/docs/source-pytorch/common/checkpointing_basic.rst b/docs/source-pytorch/common/checkpointing_basic.rst
@@ -111,7 +111,7 @@ The LightningModule also has access to the Hyperparameters
 .. code-block:: python
 
     model = MyLightningModule.load_from_checkpoint("/path/to/checkpoint.ckpt")
-    print(model.learning_rate)
+    print(model.hparams.learning_rate)
 
 ----
 
diff --git a/docs/source-pytorch/extensions/logging.rst b/docs/source-pytorch/extensions/logging.rst
@@ -137,7 +137,7 @@ The :meth:`~lightning.pytorch.core.LightningModule.log` method has a few options
 * ``logger``: Logs to the logger like ``Tensorboard``, or any other custom logger passed to the :class:`~lightning.pytorch.trainer.trainer.Trainer` (Default: ``True``).
 * ``reduce_fx``: Reduction function over step values for end of epoch. Uses :func:`torch.mean` by default and is not applied when a :class:`torchmetrics.Metric` is logged.
 * ``enable_graph``: If True, will not auto detach the graph.
-* ``sync_dist``: If True, reduces the metric across devices. Use with care as this may lead to a significant communication overhead.
+* ``sync_dist``: If True, averages the metric across devices. Use with care as this may lead to a significant communication overhead.
 * ``sync_dist_group``: The DDP group to sync across.
 * ``add_dataloader_idx``: If True, appends the index of the current dataloader to the name (when using multiple dataloaders). If False, user needs to give unique names for each dataloader to not mix the values.
 * ``batch_size``: Current batch size used for accumulating logs logged with ``on_epoch=True``. This will be directly inferred from the loaded batch, but for some data structures you might need to explicitly provide it.
diff --git a/examples/fabric/image_classifier/train_fabric.py b/examples/fabric/image_classifier/train_fabric.py
@@ -158,7 +158,7 @@ def run(hparams):
     # When using distributed training, use `fabric.save`
     # to ensure the current process is allowed to save a checkpoint
     if hparams.save_model:
-        fabric.save(model.state_dict(), "mnist_cnn.pt")
+        fabric.save(path="mnist_cnn.pt", state=model.state_dict())
 
 
 if __name__ == "__main__":
diff --git a/examples/fabric/kfold_cv/train_fabric.py b/examples/fabric/kfold_cv/train_fabric.py
@@ -161,7 +161,7 @@ def run(hparams):
     # When using distributed training, use `fabric.save`
     # to ensure the current process is allowed to save a checkpoint
     if hparams.save_model:
-        fabric.save(model.state_dict(), "mnist_cnn.pt")
+        fabric.save(path="mnist_cnn.pt", state=model.state_dict())
 
 
 if __name__ == "__main__":
diff --git a/examples/fabric/tensor_parallel/train.py b/examples/fabric/tensor_parallel/train.py
@@ -67,7 +67,7 @@ def train():
     # See `fabric consolidate --help` if you need to convert the checkpoint to a single file
     fabric.print("Saving a (distributed) checkpoint ...")
     state = {"model": model, "optimizer": optimizer, "iteration": i}
-    fabric.save("checkpoint.pt", state)
+    fabric.save(path="checkpoint.pt", state=state)
 
     fabric.print("Training successfully completed!")
     fabric.print(f"Peak memory usage: {torch.cuda.max_memory_allocated() / 1e9:.02f} GB")
diff --git a/requirements/ci.txt b/requirements/ci.txt
@@ -1,6 +1,6 @@
 setuptools <80.9.1
 wheel <0.46.0
-awscli >=1.30.0, <1.42.0
+awscli >=1.30.0, <1.43.0
 twine ==6.1.0
 importlib-metadata <9.0.0
 wget
diff --git a/requirements/docs.txt b/requirements/docs.txt
@@ -3,7 +3,7 @@ myst-parser >=0.18.1, <4.0.0
 nbsphinx >=0.8.5, <=0.9.7
 nbconvert >7.14, <7.17
 pandoc >=1.0, <=2.4
-docutils>=0.18.1,<=0.19
+docutils>=0.18.1,<=0.22
 sphinxcontrib-fulltoc >=1.0, <=1.2.0
 sphinxcontrib-mockautodoc
 sphinx-autobuild
@@ -17,7 +17,7 @@ sphinx-rtd-dark-mode
 sphinxcontrib-video ==0.4.1
 jinja2 <3.2.0
 
-lightning-utilities >=0.11.1, <0.15.0
+lightning-utilities >=0.11.1, <0.16.0
 
 # installed from S3 location and fetched in advance
 lai-sphinx-theme
diff --git a/requirements/fabric/base.txt b/requirements/fabric/base.txt
@@ -5,4 +5,4 @@ torch >=2.1.0, <2.8.0
 fsspec[http] >=2022.5.0, <2025.8.0
 packaging >=20.0, <=25.0
 typing-extensions >=4.5.0, <4.15.0
-lightning-utilities >=0.10.0, <0.15.0
+lightning-utilities >=0.10.0, <0.16.0
diff --git a/requirements/fabric/examples.txt b/requirements/fabric/examples.txt
@@ -2,4 +2,4 @@
 #  in case you want to preserve/enforce restrictions on the latest compatible version, add "strict" as an in-line comment
 
 torchvision >=0.16.0, <0.23.0
-torchmetrics >=0.10.0, <1.8.0
+torchmetrics >=0.10.0, <1.9.0
diff --git a/requirements/fabric/test.txt b/requirements/fabric/test.txt
@@ -1,4 +1,4 @@
-coverage ==7.9.2
+coverage ==7.10.2
 numpy >=1.17.2, <1.27.0
 pytest ==8.4.1
 pytest-cov ==6.2.1
diff --git a/requirements/pytorch/base.txt b/requirements/pytorch/base.txt
@@ -5,7 +5,7 @@ torch >=2.1.0, <=2.8.0
 tqdm >=4.57.0, <4.68.0
 PyYAML >5.4, <6.1.0
 fsspec[http] >=2022.5.0, <2025.8.0
-torchmetrics >0.7.0, <1.8.0
+torchmetrics >0.7.0, <1.9.0
 packaging >=20.0, <=25.0
 typing-extensions >=4.5.0, <4.15.0
-lightning-utilities >=0.10.0, <0.15.0
+lightning-utilities >=0.10.0, <0.16.0
diff --git a/requirements/pytorch/examples.txt b/requirements/pytorch/examples.txt
@@ -4,4 +4,4 @@
 requests <2.33.0
 torchvision >=0.16.0, <0.23.0
 ipython[all] <8.19.0
-torchmetrics >=0.10.0, <1.8.0
+torchmetrics >=0.10.0, <1.9.0
diff --git a/requirements/pytorch/extra.txt b/requirements/pytorch/extra.txt
@@ -6,6 +6,6 @@ matplotlib>3.1, <3.10.0
 omegaconf >=2.2.3, <2.4.0
 hydra-core >=1.2.0, <1.4.0
 jsonargparse[signatures,jsonnet] >=4.39.0, <4.41.0
-rich >=12.3.0, <14.1.0
+rich >=12.3.0, <14.2.0
 tensorboardX >=2.2, <2.7.0  # min version is set by torch.onnx missing attribute
 bitsandbytes >=0.45.2,<0.47.0; platform_system != "Darwin"
diff --git a/requirements/pytorch/test.txt b/requirements/pytorch/test.txt
@@ -1,4 +1,4 @@
-coverage ==7.9.2
+coverage ==7.10.2
 pytest ==8.4.1
 pytest-cov ==6.2.1
 pytest-timeout ==2.4.0
diff --git a/requirements/typing.txt b/requirements/typing.txt
@@ -1,4 +1,4 @@
-mypy==1.17.0
+mypy==1.17.1
 torch==2.7.1
 
 types-Markdown
diff --git a/src/lightning/fabric/CHANGELOG.md b/src/lightning/fabric/CHANGELOG.md
@@ -16,6 +16,10 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 
 -
 
+### Changed
+
+- Raise ValueError when seed is `out-of-bounds` or `cannot be cast to int` ([#21029](https://github.com/Lightning-AI/pytorch-lightning/pull/21029))
+
 
 ---
 
diff --git a/src/lightning/fabric/utilities/seed.py b/src/lightning/fabric/utilities/seed.py
@@ -27,7 +27,8 @@ def seed_everything(seed: Optional[int] = None, workers: bool = False, verbose:
     Args:
         seed: the integer value seed for global random state in Lightning.
             If ``None``, it will read the seed from ``PL_GLOBAL_SEED`` env variable. If ``None`` and the
-            ``PL_GLOBAL_SEED`` env variable is not set, then the seed defaults to 0.
+            ``PL_GLOBAL_SEED`` env variable is not set, then the seed defaults to 0. If seed is
+            not in bounds or cannot be cast to int, a ValueError is raised.
         workers: if set to ``True``, will properly configure all dataloaders passed to the
             Trainer with a ``worker_init_fn``. If the user already provides such a function
             for their dataloaders, setting this argument will have no influence. See also:
@@ -44,14 +45,12 @@ def seed_everything(seed: Optional[int] = None, workers: bool = False, verbose:
             try:
                 seed = int(env_seed)
             except ValueError:
-                seed = 0
-                rank_zero_warn(f"Invalid seed found: {repr(env_seed)}, seed set to {seed}")
+                raise ValueError(f"Invalid seed specified via PL_GLOBAL_SEED: {repr(env_seed)}")
     elif not isinstance(seed, int):
         seed = int(seed)
 
     if not (min_seed_value <= seed <= max_seed_value):
-        rank_zero_warn(f"{seed} is not in bounds, numpy accepts from {min_seed_value} to {max_seed_value}")
-        seed = 0
+        raise ValueError(f"{seed} is not in bounds, numpy accepts from {min_seed_value} to {max_seed_value}")
 
     if verbose:
         log.info(rank_prefixed_message(f"Seed set to {seed}", _get_rank()))
diff --git a/src/lightning/pytorch/CHANGELOG.md b/src/lightning/pytorch/CHANGELOG.md
@@ -10,7 +10,10 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 
 ### Added
 
-- Added `save_on_exception` option to `ModelCheckpoint` Callback
+- Added `save_on_exception` option to `ModelCheckpoint` Callback ([#20916](https://github.com/Lightning-AI/pytorch-lightning/pull/20916))
+
+
+- Added support for general mappings being returned from `training_step` when using manual optimization ([#21011](https://github.com/Lightning-AI/pytorch-lightning/pull/21011))
 
 
 ### Changed
@@ -25,8 +28,16 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 
 ### Fixed
 
--
+- fix progress bar console clearing for Rich `14.1+` ([#21016](https://github.com/Lightning-AI/pytorch-lightning/pull/21016))
+
+
+- fix `AdvancedProfiler` to handle nested profiling actions for Python 3.12+ ([#20809](https://github.com/Lightning-AI/pytorch-lightning/pull/20809))
+
+
+- Fix support for more dtypes in `ModelSummary` ([#21034](https://github.com/Lightning-AI/pytorch-lightning/pull/21034))
+
 
+- Fixed metrics in `RichProgressBar` being updated according to user provided `refresh_rate` ([#21032](https://github.com/Lightning-AI/pytorch-lightning/pull/21032))
 
 ---
 
diff --git a/src/lightning/pytorch/callbacks/progress/rich_progress.py b/src/lightning/pytorch/callbacks/progress/rich_progress.py
diff --git a/src/lightning/pytorch/loops/loop.py b/src/lightning/pytorch/loops/loop.py
diff --git a/src/lightning/pytorch/loops/optimization/manual.py b/src/lightning/pytorch/loops/optimization/manual.py
diff --git a/src/lightning/pytorch/loops/training_epoch_loop.py b/src/lightning/pytorch/loops/training_epoch_loop.py
diff --git a/src/lightning/pytorch/profilers/advanced.py b/src/lightning/pytorch/profilers/advanced.py
diff --git a/src/lightning/pytorch/strategies/xla.py b/src/lightning/pytorch/strategies/xla.py
diff --git a/src/lightning/pytorch/utilities/model_summary/model_summary.py b/src/lightning/pytorch/utilities/model_summary/model_summary.py
diff --git a/tests/tests_fabric/utilities/test_seed.py b/tests/tests_fabric/utilities/test_seed.py
diff --git a/tests/tests_pytorch/callbacks/progress/test_rich_progress_bar.py b/tests/tests_pytorch/callbacks/progress/test_rich_progress_bar.py
diff --git a/tests/tests_pytorch/loops/test_double_iter_in_iterable_dataset.py b/tests/tests_pytorch/loops/test_double_iter_in_iterable_dataset.py
diff --git a/tests/tests_pytorch/profilers/test_profiler.py b/tests/tests_pytorch/profilers/test_profiler.py
diff --git a/tests/tests_pytorch/trainer/optimization/test_manual_optimization.py b/tests/tests_pytorch/trainer/optimization/test_manual_optimization.py
diff --git a/tests/tests_pytorch/utilities/test_model_summary.py b/tests/tests_pytorch/utilities/test_model_summary.py
