Merge branch 'master' into fix/save-last-checkpoint

Author: Borda

.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
 
@@ -109,6 +109,50 @@ ______________________________________________________________________
 
 ## Guidelines
 
+### Development environment
+
+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 forked repository:
+
+```bash
+git clone https://github.com/{YOUR_GITHUB_USERNAME}/pytorch-lightning.git
+cd pytorch-lightning
+```
+
+> 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
+# uv venv --python 3.11 # use this instead if you need a specific python version
+
+source .venv/bin/activate # command may differ based on your shell
+uv pip install ".[dev, examples]"
+```
+
+Once the dependencies have been installed, install pre-commit and set up the git hook scripts:
+
+```bash
+uv pip install pre-commit
+pre-commit install
+```
+
+If you would like more information regarding the uv commands, please refer to uv's documentation for more information on their [pip interface](https://docs.astral.sh/uv/pip/).
+
 ### Developments scripts
 
 To build the documentation locally, simply execute the following commands from project root (only for Unix):

.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
 

.github/markdown-links-config.json

@@ -22,5 +22,9 @@
         "Accept-Encoding": "zstd, br, gzip, deflate"
       }
     }
-  ]
+  ],
+  "timeout": "20s",
+  "retryOn429": true,
+  "retryCount": 5,
+  "fallbackRetryDelay": "20s"
 }

.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' }}

.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

.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

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")

README.md

@@ -55,6 +55,12 @@ ______________________________________________________________________
 
  
 
+# Why PyTorch Lightning?   
+
+Training models in plain PyTorch is tedious and error-prone - you have to manually handle things like backprop, mixed precision, multi-GPU, and distributed training, often rewriting code for every new project. PyTorch Lightning organizes PyTorch code to automate those complexities so you can focus on your model and data, while keeping full control and scaling from CPU to multi-node without changing your core code. But if you want control of those things, you can still opt into more DIY.   
+
+Fun analogy: If PyTorch is Javascript, PyTorch Lightning is ReactJS or NextJS.
+
 # Lightning has 2 core packages
 
 [PyTorch Lightning: Train and deploy PyTorch at scale](#why-pytorch-lightning).

_notebooks

@@ -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%.*} && \