Merge branch 'master' into dependabot-github_actions-Lightning-AI-utilities-0.15.0

Borda · web-flow · commit 069e798b9c59 · 2025-08-04T15:00:26.000+03:00
diff --git a/docs/source-fabric/advanced/model_parallel/tp_fsdp.rst b/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>
 
diff --git a/docs/source-pytorch/advanced/model_parallel/tp.rst b/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>
 
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/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/pytorch/callbacks/progress/rich_progress.py b/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()

Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`		`-coverage ==7.9.2`
	`1`	`+coverage ==7.10.2`
`2`	`2`	`numpy >=1.17.2, <1.27.0`
`3`	`3`	`pytest ==8.4.1`
`4`	`4`	`pytest-cov ==6.2.1`