Merge branch 'master' into bugfix/20852_add-support-for-xla2.7-which-deprecated-methods

Author: deependujha

.github/CONTRIBUTING.md

@@ -3,7 +3,7 @@
 Welcome to the PyTorch Lightning community! We're building the most advanced research platform on the planet to implement the latest, best practices
 and integrations that the amazing PyTorch team and other research organization rolls out!
 
-If you are new to open source, check out [this blog to get started with your first Open Source contribution](https://devblog.pytorchlightning.ai/quick-contribution-guide-86d977171b3a).
+If you are new to open source, check out [this blog to get started with your first Open Source contribution](https://medium.com/pytorch-lightning/quick-contribution-guide-86d977171b3a).
 
 ## Main Core Value: One less thing to remember
 

docs/source-fabric/advanced/model_parallel/tp_fsdp.rst

@@ -9,7 +9,7 @@ The :doc:`Tensor Parallelism documentation <tp>` and a general understanding of
 
 .. raw:: html
 
-    <a target="_blank" href="https://lightning.ai/lightning-ai/studios/tensor-parallelism-supercharging-large-model-training-with-lightning-fabric">
+    <a target="_blank" href="https://lightning.ai/lightning-ai/studios/pretrain-an-llm-with-pytorch-lightning">
       <img src="https://pl-bolts-doc-images.s3.us-east-2.amazonaws.com/app-2/studio-badge.svg" alt="Open In Studio" style="width: auto; max-width: none;"/>
     </a>
 

docs/source-pytorch/advanced/model_parallel/tp.rst

@@ -8,7 +8,7 @@ This method is most effective for models with very large layers, significantly e
 
 .. raw:: html
 
-    <a target="_blank" href="https://lightning.ai/lightning-ai/studios/tensor-parallelism-supercharging-large-model-training-with-pytorch-lightning">
+    <a target="_blank" href="https://lightning.ai/lightning-ai/studios/pretrain-an-llm-with-pytorch-lightning">
       <img src="https://pl-bolts-doc-images.s3.us-east-2.amazonaws.com/app-2/studio-badge.svg" alt="Open In Studio" style="width: auto; max-width: none;"/>
     </a>
 

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 >=0.16, <0.22
+docutils>=0.18.1,<=0.19
 sphinxcontrib-fulltoc >=1.0, <=1.2.0
 sphinxcontrib-mockautodoc
 sphinx-autobuild

requirements/fabric/base.txt

@@ -2,7 +2,7 @@
 #  in case you want to preserve/enforce restrictions on the latest compatible version, add "strict" as an in-line comment
 
 torch >=2.1.0, <2.8.0
-fsspec[http] >=2022.5.0, <2025.6.0
+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

requirements/pytorch/base.txt

@@ -4,7 +4,7 @@
 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, <2025.6.0
+fsspec[http] >=2022.5.0, <2025.8.0
 torchmetrics >0.7.0, <1.8.0
 packaging >=20.0, <=25.0
 typing-extensions >=4.5.0, <4.15.0

requirements/pytorch/test.txt

@@ -16,4 +16,4 @@ 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, <2.20.0  # for `TensorBoardLogger`
+tensorboard >=2.9.1, <2.21.0  # for `TensorBoardLogger`

requirements/typing.txt

@@ -1,4 +1,4 @@
-mypy==1.16.1
+mypy==1.17.0
 torch==2.7.1
 
 types-Markdown

src/lightning/pytorch/callbacks/progress/rich_progress.py

@@ -447,6 +447,11 @@ def _add_task(self, total_batches: Union[int, float], description: str, visible:
             visible=visible,
         )
 
+    def _initialize_train_progress_bar_id(self) -> None:
+        total_batches = self.total_train_batches
+        train_description = self._get_train_description(self.trainer.current_epoch)
+        self.train_progress_bar_id = self._add_task(total_batches, train_description)
+
     def _update(self, progress_bar_id: Optional["TaskID"], current: int, visible: bool = True) -> None:
         if self.progress is not None and self.is_enabled:
             assert progress_bar_id is not None
@@ -531,6 +536,9 @@ def on_train_batch_end(
         batch: Any,
         batch_idx: int,
     ) -> None:
+        if not self.is_disabled and self.train_progress_bar_id is None:
+            # can happen when resuming from a mid-epoch restart
+            self._initialize_train_progress_bar_id()
         self._update(self.train_progress_bar_id, batch_idx + 1)
         self._update_metrics(trainer, pl_module)
         self.refresh()

src/pytorch_lightning/README.md

@@ -370,7 +370,7 @@ The PyTorch Lightning community is maintained by
 - [10+ core contributors](https://lightning.ai/docs/pytorch/stable/community/governance.html) who are all a mix of professional engineers, Research Scientists, and Ph.D. students from top AI labs.
 - 680+ active community contributors.
 
-Want to help us build Lightning and reduce boilerplate for thousands of researchers? [Learn how to make your first contribution here](https://devblog.pytorchlightning.ai/quick-contribution-guide-86d977171b3a)
+Want to help us build Lightning and reduce boilerplate for thousands of researchers? [Learn how to make your first contribution here](https://medium.com/pytorch-lightning/quick-contribution-guide-86d977171b3a)
 
 PyTorch Lightning is also part of the [PyTorch ecosystem](https://pytorch.org/ecosystem/) which requires projects to have solid testing, documentation and support.