Merge branch 'master' into feature/19743-tensorboard-histograms

Author: Borda

.github/workflows/ci-tests-fabric.yml

@@ -96,7 +96,7 @@ jobs:
         run: |
           cd requirements/fabric
           pip install -U "lightning-utilities[cli]"
-          python -m lightning_utilities.cli requirements set-oldest --req_files "['base.txt', 'strategies.txt']"
+          python -m lightning_utilities.cli requirements set-oldest --req_files "['base.txt', 'strategies.txt', 'test.txt']"
           pip install "cython<3.0" wheel
           pip install "pyyaml==5.4" --no-build-isolation
 
@@ -142,7 +142,8 @@ jobs:
         run: |
           pip install -e ".[${EXTRA_PREFIX}test,${EXTRA_PREFIX}strategies]" \
             -U --upgrade-strategy=eager --prefer-binary \
-            --extra-index-url="${TORCH_URL}" --find-links="${PYPI_CACHE_DIR}"
+            --extra-index-url="${TORCH_URL}" \
+            --find-links="${PYPI_CACHE_DIR}"
           pip list
       - name: Dump handy wheels
         if: github.event_name == 'push' && github.ref == 'refs/heads/master'

.github/workflows/ci-tests-pytorch.yml

@@ -101,7 +101,7 @@ jobs:
         run: |
           cd requirements/pytorch
           pip install -U "lightning-utilities[cli]"
-          python -m lightning_utilities.cli requirements set-oldest --req_files "['base.txt', 'extra.txt', 'strategies.txt', 'examples.txt']"
+          python -m lightning_utilities.cli requirements set-oldest --req_files "['base.txt', 'extra.txt', 'strategies.txt', 'examples.txt', 'test.txt']"
           pip install "cython<3.0" wheel
           pip install "pyyaml==5.4" --no-build-isolation
 
@@ -141,7 +141,9 @@ jobs:
           pip install ".[${EXTRA_PREFIX}extra,${EXTRA_PREFIX}test,${EXTRA_PREFIX}strategies]" \
             -U --upgrade-strategy=eager --prefer-binary \
             -r requirements/_integrations/accelerators.txt \
-            --extra-index-url="${TORCH_URL}" --find-links="${PYPI_CACHE_DIR}" --find-links="https://download.pytorch.org/whl/torch-tensorrt"
+            --extra-index-url="${TORCH_URL}" \
+            --find-links="${PYPI_CACHE_DIR}" \
+            --find-links="https://download.pytorch.org/whl/torch-tensorrt"
           pip list
       - name: Drop LAI from extensions
         if: ${{ matrix.pkg-name != 'lightning' }}

docs/source-pytorch/conf.py

@@ -127,7 +127,7 @@ def _load_py_module(name: str, location: str) -> ModuleType:
         "https://pytorch.org/docs/stable/", "https://pytorch.org/docs/{torch.__version__}/", _PATH_ROOT
     )
     adjust_linked_external_docs(
-        "https://lightning.ai/docs/torchmetrics", "https://lightning.ai/docs/torchmetrics/v{torchmetrics.__version__}/", _PATH_ROOT, version_digits=3
+        "https://lightning.ai/docs/torchmetrics/stable/", "https://lightning.ai/docs/torchmetrics/v{torchmetrics.__version__}/", _PATH_ROOT, version_digits=3
     )
     adjust_linked_external_docs(
         "https://lightning.ai/docs/fabric/stable/", "https://lightning.ai/docs/fabric/{lightning_fabric.__version__}/", _PATH_ROOT, version_digits=3

docs/source-pytorch/extensions/logging.rst

@@ -120,6 +120,10 @@ methods to log from anywhere in a :doc:`LightningModule <../common/lightning_mod
 .. note::
     Everything explained below applies to both :meth:`~lightning.pytorch.core.LightningModule.log` or :meth:`~lightning.pytorch.core.LightningModule.log_dict` methods.
 
+.. note::
+
+    When using TorchMetrics with Lightning, we recommend referring to the `TorchMetrics Lightning integration documentation <https://lightning.ai/docs/torchmetrics/stable/pages/lightning.html>`_ for logging best practices, common pitfalls, and proper usage patterns.
+
 Depending on where the :meth:`~lightning.pytorch.core.LightningModule.log` method is called, Lightning auto-determines
 the correct logging mode for you. Of course you can override the default behavior by manually setting the
 :meth:`~lightning.pytorch.core.LightningModule.log` parameters.

requirements/fabric/test.txt

@@ -1,10 +1,10 @@
 coverage ==7.10.4
-numpy >=1.17.2, <1.27.0
+numpy >=1.21.0, <1.27.0
 pytest ==8.4.1
 pytest-cov ==6.2.1
 pytest-timeout ==2.4.0
 pytest-rerunfailures ==15.1
 pytest-random-order ==1.2.0
 click ==8.1.8; python_version < "3.11"
 click ==8.2.1; python_version > "3.10"
-tensorboardX >=2.2, <2.7.0  # min version is set by torch.onnx missing attribute
+tensorboardX >=2.6, <2.7.0  # todo: relax it back to `>=2.2` after fixing tests

requirements/pytorch/loggers.info

@@ -4,4 +4,4 @@ neptune >=1.0.0
 comet-ml >=3.31.0
 mlflow >=1.0.0
 wandb >=0.12.10
-tensorboard >=2.9.1
+tensorboard >=2.11

requirements/pytorch/test.txt

@@ -8,16 +8,16 @@ pytest-random-order ==1.2.0
 # needed in tests
 cloudpickle >=1.3, <3.2.0
 scikit-learn >0.22.1, <1.8.0
-numpy >=1.17.2, <1.27.0
-onnx >=1.12.0, <1.19.0
+numpy >1.20.0, <1.27.0
+onnx >1.12.0, <1.19.0
 onnxruntime >=1.12.0, <1.23.0
-onnxscript >= 0.2.2, <0.4.0
+onnxscript >= 0.1.0, <0.4.0
 psutil <7.0.1 # for `DeviceStatsMonitor`
 pandas >2.0, <2.4.0  # needed in benchmarks
 fastapi  # for `ServableModuleValidator`  # not setting version as re-defined in App
 uvicorn  # for `ServableModuleValidator`  # not setting version as re-defined in App
 
-tensorboard >=2.9.1, <2.21.0  # for `TensorBoardLogger`
+tensorboard >=2.11, <2.21.0  # for `TensorBoardLogger`
 
 --find-links https://download.pytorch.org/whl/torch-tensorrt
 torch-tensorrt; platform_system == "Linux" and python_version >= "3.12"

src/lightning/pytorch/CHANGELOG.md

@@ -40,6 +40,8 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 - Fixed learning rate not being correctly set after using `LearningRateFinder` callback ([#21068](https://github.com/Lightning-AI/pytorch-lightning/pull/21068))
 
 
+- Fixed misalignment column while using rich model summary in `DeepSpeedstrategy` ([#21100](https://github.com/Lightning-AI/pytorch-lightning/pull/21100))
+
 ---
 
 ## [2.5.3] - 2025-08-13

src/lightning/pytorch/callbacks/rich_model_summary.py

@@ -79,18 +79,21 @@ def summarize(
         from rich.table import Table
 
         console = get_console()
+        column_names = list(zip(*summary_data))[0]
 
         header_style: str = summarize_kwargs.get("header_style", "bold magenta")
         table = Table(header_style=header_style)
         table.add_column(" ", style="dim")
         table.add_column("Name", justify="left", no_wrap=True)
         table.add_column("Type")
         table.add_column("Params", justify="right")
+
+        if "Params per Device" in column_names:
+            table.add_column("Params per Device", justify="right")
+
         table.add_column("Mode")
         table.add_column("FLOPs", justify="right")
 
-        column_names = list(zip(*summary_data))[0]
-
         for column_name in ["In sizes", "Out sizes"]:
             if column_name in column_names:
                 table.add_column(column_name, justify="right", style="white")

src/lightning/pytorch/utilities/model_summary/model_summary_deepspeed.py

@@ -99,6 +99,7 @@ def _get_summary_data(self) -> list[tuple[str, list[str]]]:
             ("Params", list(map(get_human_readable_count, self.param_nums))),
             ("Params per Device", list(map(get_human_readable_count, self.parameters_per_layer))),
             ("Mode", ["train" if mode else "eval" for mode in self.training_modes]),
+            ("FLOPs", list(map(get_human_readable_count, (sum(x.values()) for x in self.flop_counts.values())))),
         ]
         if self._model.example_input_array is not None:
             arrays.append(("In sizes", [str(x) for x in self.in_sizes]))