docs: update pytorch_lightning imports

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

@@ -230,7 +230,7 @@ jobs:
         timeout-minutes: 55
 
   build-docs:
-    # if: github.event.pull_request.draft == false  # fixme
+    if: github.event.pull_request.draft == false
     runs-on: ubuntu-20.04
     steps:
       - uses: actions/checkout@v3

.github/workflows/docs-checks.yml

@@ -65,12 +65,6 @@ jobs:
           key: docs-test-${{ matrix.pkg-name }}-${{ hashFiles('requirements/${{ matrix.pkg-name }}/*.txt') }}
           restore-keys: docs-test-${{ matrix.pkg-name }}-
 
-      - name: Install LAI package
-        # This is needed as App docs is heavily using/referring to lightning package
-        if: ${{ matrix.pkg-name == 'lightning' }}
-        run: |
-          pip install -e . -U -v -f pypi -f ${TORCH_URL}
-
       - name: Adjust docs refs
         if: ${{ matrix.pkg-name == 'lightning' }}
         run: |
@@ -85,8 +79,6 @@ jobs:
           python -c "n = '${{ matrix.pkg-name }}' ; print('REQ_DIR=' + {'lightning': 'app'}.get(n, n))" >> $GITHUB_ENV
 
       - name: Install this package
-        env:
-          PACKAGE_NAME: ${{ matrix.pkg-name }}
         run: |
           pip install -e .[extra,cloud,ui] -U -r requirements/${{ env.REQ_DIR }}/docs.txt -f pypi -f ${TORCH_URL}
           pip list
@@ -138,8 +130,6 @@ jobs:
           python -c "n = '${{ matrix.pkg-name }}' ; print('REQ_DIR=' + {'lightning': 'app'}.get(n, n))" >> $GITHUB_ENV
 
       - name: Install package & dependencies
-        env:
-          PACKAGE_NAME: ${{ matrix.pkg-name }}
         run: |
           pip --version
           pip install -e . -U -r requirements/${{ env.REQ_DIR }}/docs.txt -f pypi -f ${TORCH_URL}
@@ -148,19 +138,15 @@ jobs:
 
       - name: Make Documentation
         working-directory: ./docs/${{ env.DOCS_DIR }}
-        run: |
-          make html --debug --jobs $(nproc) SPHINXOPTS="-W --keep-going"
+        run: make html --debug --jobs $(nproc) SPHINXOPTS="-W --keep-going"
 
       - name: Check External Links in Sphinx Documentation (Optional)
         working-directory: ./docs/${{ env.DOCS_DIR }}
-        run: |
-          make linkcheck
+        run: make linkcheck
         continue-on-error: true
 
       - name: Upload built docs
         uses: actions/upload-artifact@v3
         with:
           name: docs-${{ matrix.pkg-name }}-${{ github.sha }}
           path: docs/build/html/
-        # Use always() to always run this step to publish test results when there are test failuress
-        if: success()

docs/source-pytorch/accelerators/accelerator_prepare.rst

@@ -50,7 +50,7 @@ This will make your code scale to any arbitrary number of GPUs or TPUs with Ligh
         z = torch.Tensor(2, 3)
         z = z.to(x)
 
-The :class:`~pytorch_lightning.core.module.LightningModule` knows what device it is on. You can access the reference via ``self.device``.
+The :class:`~lightning.pytorch.core.module.LightningModule` knows what device it is on. You can access the reference via ``self.device``.
 Sometimes it is necessary to store tensors as module attributes. However, if they are not parameters they will
 remain on the CPU even if the module gets moved to a new device. To prevent that and remain device agnostic,
 register the tensor as a buffer in your modules' ``__init__`` method with :meth:`~torch.nn.Module.register_buffer`.

docs/source-pytorch/accelerators/gpu_intermediate.rst

@@ -228,9 +228,9 @@ DDP can also be used with 1 GPU, but there's no reason to do so other than debug
 
 Implement Your Own Distributed (DDP) training
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-If you need your own way to init PyTorch DDP you can override :meth:`pytorch_lightning.strategies.ddp.DDPStrategy.setup_distributed`.
+If you need your own way to init PyTorch DDP you can override :meth:`lightning.pytorch.strategies.ddp.DDPStrategy.setup_distributed`.
 
-If you also need to use your own DDP implementation, override :meth:`pytorch_lightning.strategies.ddp.DDPStrategy.configure_ddp`.
+If you also need to use your own DDP implementation, override :meth:`lightning.pytorch.strategies.ddp.DDPStrategy.configure_ddp`.
 
 ----------
 
@@ -279,7 +279,7 @@ Lightning allows explicitly specifying the backend via the `process_group_backen
 
 .. code-block:: python
 
-    from pytorch_lightning.strategies import DDPStrategy
+    from lightning.pytorch.strategies import DDPStrategy
 
     # Explicitly specify the process group backend if you choose to
     ddp = DDPStrategy(process_group_backend="nccl")

docs/source-pytorch/accelerators/hpu_basic.rst

@@ -46,7 +46,7 @@ To enable PyTorch Lightning to utilize the HPU accelerator, simply provide ``acc
 
 
 The ``devices>1`` parameter with HPUs enables the Habana accelerator for distributed training.
-It uses :class:`~pytorch_lightning.strategies.hpu_parallel.HPUParallelStrategy` internally which is based on DDP
+It uses :class:`~lightning.pytorch.strategies.hpu_parallel.HPUParallelStrategy` internally which is based on DDP
 strategy with the addition of Habana's collective communication library (HCCL) to support scale-up within a node and
 scale-out across multiple nodes.
 

docs/source-pytorch/accelerators/hpu_intermediate.rst

@@ -23,21 +23,21 @@ By default, HPU training will use 32-bit precision. To enable mixed precision, s
 Customize Mixed Precision
 -------------------------
 
-Internally, :class:`~pytorch_lightning.plugins.precision.hpu.HPUPrecisionPlugin` uses the Habana Mixed Precision (HMP) package to enable mixed precision training.
+Internally, :class:`~lightning.pytorch.plugins.precision.hpu.HPUPrecisionPlugin` uses the Habana Mixed Precision (HMP) package to enable mixed precision training.
 
 You can execute the ops in FP32 or BF16 precision. The HMP package modifies the Python operators to add the appropriate cast operations for the arguments before execution.
 The default settings enable users to enable mixed precision training with minimal code easily.
 
 In addition to the default settings in HMP, users also have the option of overriding these defaults and providing their
-BF16 and FP32 operator lists by passing them as parameter to :class:`~pytorch_lightning.plugins.precision.hpu.HPUPrecisionPlugin`.
+BF16 and FP32 operator lists by passing them as parameter to :class:`~lightning.pytorch.plugins.precision.hpu.HPUPrecisionPlugin`.
 
 The below snippet shows an example model using MNIST with a single Habana Gaudi device and making use of HMP by overriding the default parameters.
 This enables advanced users to provide their own BF16 and FP32 operator list instead of using the HMP defaults.
 
 .. code-block:: python
 
-    import pytorch_lightning as pl
-    from pytorch_lightning.plugins import HPUPrecisionPlugin
+    import lightning.pytorch as pl
+    from lightning.pytorch.plugins import HPUPrecisionPlugin
 
     # Initialize a trainer with HPU accelerator for HPU strategy for single device,
     # with mixed precision using overidden HMP settings
@@ -72,7 +72,7 @@ For more details, please refer to `PyTorch Mixed Precision Training on Gaudi <ht
 Enabling DeviceStatsMonitor with HPUs
 ----------------------------------------
 
-:class:`~pytorch_lightning.callbacks.device_stats_monitor.DeviceStatsMonitor` is a callback that automatically monitors and logs device stats during the training stage.
+:class:`~lightning.pytorch.callbacks.device_stats_monitor.DeviceStatsMonitor` is a callback that automatically monitors and logs device stats during the training stage.
 This callback can be passed for training with HPUs. It returns a map of the following metrics with their values in bytes of type uint64:
 
 - **Limit**: amount of total memory on HPU device.
@@ -90,8 +90,8 @@ The below snippet shows how DeviceStatsMonitor can be enabled.
 
 .. code-block:: python
 
-    from pytorch_lightning import Trainer
-    from pytorch_lightning.callbacks import DeviceStatsMonitor
+    from lightning.pytorch import Trainer
+    from lightning.pytorch.callbacks import DeviceStatsMonitor
 
     device_stats = DeviceStatsMonitor()
     trainer = Trainer(accelerator="hpu", callbacks=[device_stats])

docs/source-pytorch/accelerators/ipu_advanced.rst

@@ -19,8 +19,8 @@ IPUs provide further optimizations to speed up training. By using the ``IPUStrat
 
 .. code-block:: python
 
-    import pytorch_lightning as pl
-    from pytorch_lightning.strategies import IPUStrategy
+    import lightning.pytorch as pl
+    from lightning.pytorch.strategies import IPUStrategy
 
     model = MyLightningModule()
     trainer = pl.Trainer(accelerator="ipu", devices=8, strategy=IPUStrategy(device_iterations=32))
@@ -31,8 +31,8 @@ Note that by default we return the last device iteration loss. You can override
 .. code-block:: python
 
     import poptorch
-    import pytorch_lightning as pl
-    from pytorch_lightning.strategies import IPUStrategy
+    import lightning.pytorch as pl
+    from lightning.pytorch.strategies import IPUStrategy
 
     model = MyLightningModule()
     inference_opts = poptorch.Options()
@@ -71,7 +71,7 @@ Below is an example using the block annotation in a LightningModule.
 
 .. code-block:: python
 
-    import pytorch_lightning as pl
+    import lightning.pytorch as pl
     import poptorch
 
 
@@ -104,7 +104,7 @@ You can also use the block context manager within the forward function, or any o
 
 .. code-block:: python
 
-    import pytorch_lightning as pl
+    import lightning.pytorch as pl
     import poptorch
 
 

docs/source-pytorch/accelerators/ipu_basic.rst

@@ -70,5 +70,5 @@ Please see the `MNIST example <https://github.com/Lightning-AI/lightning/blob/ma
 * Since the step functions are traced, branching logic or any form of primitive values are traced into constants. Be mindful as this could lead to errors in your custom code.
 * Clipping gradients is not supported.
 * It is not possible to use :class:`torch.utils.data.BatchSampler` in your dataloaders if you are using multiple IPUs.
-* IPUs handle the data transfer to the device on the host, hence the hooks :meth:`~pytorch_lightning.core.hooks.ModelHooks.transfer_batch_to_device` and
-  :meth:`~pytorch_lightning.core.hooks.ModelHooks.on_after_batch_transfer` do not apply here and if you have overridden any of them, an exception will be raised.
+* IPUs handle the data transfer to the device on the host, hence the hooks :meth:`~lightning.pytorch.core.hooks.ModelHooks.transfer_batch_to_device` and
+  :meth:`~lightning.pytorch.core.hooks.ModelHooks.on_after_batch_transfer` do not apply here and if you have overridden any of them, an exception will be raised.

docs/source-pytorch/accelerators/ipu_intermediate.rst

@@ -20,7 +20,7 @@ set the precision flag.
 
 .. code-block:: python
 
-    import pytorch_lightning as pl
+    import lightning.pytorch as pl
 
     model = MyLightningModule()
     trainer = pl.Trainer(accelerator="ipu", devices=8, precision=16)
@@ -30,8 +30,8 @@ You can also use pure 16-bit training, where the weights are also in 16-bit prec
 
 .. code-block:: python
 
-    import pytorch_lightning as pl
-    from pytorch_lightning.strategies import IPUStrategy
+    import lightning.pytorch as pl
+    from lightning.pytorch.strategies import IPUStrategy
 
     model = MyLightningModule()
     model = model.half()
@@ -53,8 +53,8 @@ Lightning supports dumping all reports to a directory to open using the tool.
 
 .. code-block:: python
 
-    import pytorch_lightning as pl
-    from pytorch_lightning.strategies import IPUStrategy
+    import lightning.pytorch as pl
+    from lightning.pytorch.strategies import IPUStrategy
 
     model = MyLightningModule()
     trainer = pl.Trainer(accelerator="ipu", devices=8, strategy=IPUStrategy(autoreport_dir="report_dir/"))

docs/source-pytorch/accelerators/tpu_advanced.rst

@@ -25,9 +25,9 @@ Example:
 
 .. code-block:: python
 
-    from pytorch_lightning.core.module import LightningModule
+    from lightning.pytorch.core.module import LightningModule
     from torch import nn
-    from pytorch_lightning.trainer.trainer import Trainer
+    from lightning.pytorch.trainer.trainer import Trainer
 
 
     class WeightSharingModule(LightningModule):

docs/source-pytorch/accelerators/tpu_faq.rst

@@ -18,7 +18,7 @@ XLA configuration is missing?
     ...
     File "/home/kaushikbokka/pytorch-lightning/pytorch_lightning/utilities/device_parser.py", line 125, in parse_tpu_cores
         raise MisconfigurationException('No TPU devices were found.')
-    pytorch_lightning.utilities.exceptions.MisconfigurationException: No TPU devices were found.
+    lightning.pytorch.utilities.exceptions.MisconfigurationException: No TPU devices were found.
 
 This means the system is missing XLA configuration. You would need to set up XRT TPU device configuration.
 
@@ -88,7 +88,7 @@ How to setup the debug mode for Training on TPUs?
 
 .. code-block:: python
 
-    import pytorch_lightning as pl
+    import lightning.pytorch as pl
 
     my_model = MyLightningModule()
     trainer = pl.Trainer(accelerator="tpu", devices=8, strategy="xla_debug")

docs/source-pytorch/accelerators/tpu_intermediate.rst

@@ -42,7 +42,7 @@ To use a full TPU pod skip to the TPU pod section.
 
 .. code-block:: python
 
-    import pytorch_lightning as pl
+    import lightning.pytorch as pl
 
     my_model = MyLightningModule()
     trainer = pl.Trainer(accelerator="tpu", devices=8)
@@ -105,7 +105,7 @@ set the 16-bit flag.
 
 .. code-block:: python
 
-    import pytorch_lightning as pl
+    import lightning.pytorch as pl
 
     my_model = MyLightningModule()
     trainer = pl.Trainer(accelerator="tpu", devices=8, precision=16)