pytorch · shoumikhin · Mar 31, 2025 · Mar 31, 2025 · Mar 31, 2025 · Mar 31, 2025
diff --git a/.github/workflows/apple.yml b/.github/workflows/apple.yml
@@ -37,7 +37,7 @@ jobs:
         id: set_version
         shell: bash
         run: |
-          VERSION="0.5.0.$(TZ='PST8PDT' date +%Y%m%d)"
+          VERSION="0.6.0"
           echo "version=$VERSION" >> "$GITHUB_OUTPUT"
 
   build-demo-ios:
@@ -212,7 +212,7 @@ jobs:
           name: executorch-frameworks-ios
           path: ${{ runner.temp }}/frameworks-ios/
       - name: Only push to S3 when running the workflow manually from main branch
-        if: ${{ (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch') && github.ref == 'refs/heads/main' }}
+        if: ${{ (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch') && github.ref == 'refs/heads/release/0.6' }}
         shell: bash
         run: |
           echo "UPLOAD_ON_MAIN=1" >> "${GITHUB_ENV}"

@@ -39,33 +39,32 @@ To build the documentation locally:
 
 1. Clone the ExecuTorch repo to your machine.
 
-1. If you don't have it already, start a conda environment:
+   ```bash
+   git clone -b release/0.6 https://github.com/pytorch/executorch.git && cd executorch
+   ```
 
-   ```{note}
-   The below command generates a completely new environment and resets
-   any existing dependencies. If you have an environment already, skip
-   the `conda create` command.
+1. If you don't have it already, start either a Python virtual envitonment:
+
+   ```bash
+   python3 -m venv .venv && source .venv/bin/activate && pip install --upgrade pip
    ```
 
+   Or a Conda environment:
+
    ```bash
-   conda create -yn executorch python=3.10.0
-   conda activate executorch
+   conda create -yn executorch python=3.10.0 && conda activate executorch
    ```
 
 1. Install dependencies:
 
    ```bash
    pip3 install -r ./.ci/docker/requirements-ci.txt
    ```
-1. Update submodules
 
-   ```bash
-   git submodule sync && git submodule update --init
-   ```
 1. Run:
 
    ```bash
-   bash install_executorch.sh
+   ./install_executorch.sh
    ```
 
 1. Go to the `docs/` directory.

@@ -137,7 +137,7 @@ For a full example of running a model on Android, see the [DeepLabV3AndroidDemo]
 #### Installation
 ExecuTorch supports both iOS and MacOS via C++, as well as hardware backends for CoreML, MPS, and CPU. The iOS runtime library is provided as a collection of .xcframework targets and are made available as a Swift PM package.
 
-To get started with Xcode, go to File > Add Package Dependencies. Paste the URL of the ExecuTorch repo into the search bar and select it. Make sure to change the branch name to the desired ExecuTorch version in format “swiftpm-”, (e.g. “swiftpm-0.5.0”).  The ExecuTorch dependency can also be added to the package file manually. See [Using ExecuTorch on iOS](using-executorch-ios.md) for more information.
+To get started with Xcode, go to File > Add Package Dependencies. Paste the URL of the ExecuTorch repo into the search bar and select it. Make sure to change the branch name to the desired ExecuTorch version in format “swiftpm-”, (e.g. “swiftpm-0.6.0”).  The ExecuTorch dependency can also be added to the package file manually. See [Using ExecuTorch on iOS](using-executorch-ios.md) for more information.
 
 #### Runtime APIs
 Models can be loaded and run from Objective-C using the C++ APIs.

@@ -43,15 +43,17 @@ Instructions on installing miniconda can be [found here](https://docs.anaconda.c
 mkdir et-nanogpt
 cd et-nanogpt
 
-# Clone the ExecuTorch repository and submodules.
+# Clone the ExecuTorch repository.
 mkdir third-party
-git clone -b release/0.4 https://github.com/pytorch/executorch.git third-party/executorch
-cd third-party/executorch
-git submodule update --init
+git clone -b release/0.6 https://github.com/pytorch/executorch.git third-party/executorch && cd third-party/executorch
 
-# Create a conda environment and install requirements.
-conda create -yn executorch python=3.10.0
-conda activate executorch
+# Create either a Python virtual environment:
+python3 -m venv .venv && source .venv/bin/activate && pip install --upgrade pip
+
+# Or a Conda environment:
+conda create -yn executorch python=3.10.0 && conda activate executorch
+
+# Install requirements
 ./install_executorch.sh
 
 cd ../..
@@ -76,11 +78,8 @@ pyenv install -s 3.10
 pyenv virtualenv 3.10 executorch
 pyenv activate executorch
 
-# Clone the ExecuTorch repository and submodules.
-mkdir third-party
-git clone -b release/0.4 https://github.com/pytorch/executorch.git third-party/executorch
-cd third-party/executorch
-git submodule update --init
+# Clone the ExecuTorch repository.
+git clone -b release/0.6 https://github.com/pytorch/executorch.git third-party/executorch && cd third-party/executorch
 
 # Install requirements.
 PYTHON_EXECUTABLE=python ./install_executorch.sh

@@ -36,27 +36,23 @@ portability details.
 
 ## Environment Setup
 
-### Create a Virtual Environment
+### Clone ExecuTorch
 
-[Install conda on your machine](https://conda.io/projects/conda/en/latest/user-guide/install/index.html). Then, create a virtual environment to manage our dependencies.
    ```bash
-   # Create and activate a conda environment named "executorch"
-   conda create -yn executorch python=3.10.0
-   conda activate executorch
+   # Clone the ExecuTorch repo from GitHub
+   git clone -b release/0.6 https://github.com/pytorch/executorch.git && cd executorch
    ```
 
-### Clone ExecuTorch
+### Create a Virtual Environment
 
+Create and activate a Python virtual environment:
    ```bash
-   # Clone the ExecuTorch repo from GitHub
-   # 'main' branch is the primary development branch where you see the latest changes.
-   # 'viable/strict' contains all of the commits on main that pass all of the necessary CI checks.
-   git clone --branch viable/strict https://github.com/pytorch/executorch.git
-   cd executorch
-
-   # Update and pull submodules
-   git submodule sync
-   git submodule update --init
+   python3 -m venv .venv && source .venv/bin/activate && pip install --upgrade pip
+   ```
+
+Or alternatively, [install conda on your machine](https://conda.io/projects/conda/en/latest/user-guide/install/index.html). Then, create a Conda environment named "executorch".
+   ```bash
+   conda create -yn executorch python=3.10.0 && conda activate executorch
    ```
 
 ## Install ExecuTorch pip package from Source

@@ -25,7 +25,7 @@ The prebuilt ExecuTorch runtime, backend, and kernels are available as a [Swift
 
 #### Xcode
 
-In Xcode, go to `File > Add Package Dependencies`. Paste the URL of the [ExecuTorch repo](https://github.com/pytorch/executorch) into the search bar and select it. Make sure to change the branch name to the desired ExecuTorch version in format "swiftpm-<version>", (e.g. "swiftpm-0.5.0"), or a branch name in format "swiftpm-<version>.<year_month_date>" (e.g. "swiftpm-0.5.0-20250228") for a nightly build on a specific date.
+In Xcode, go to `File > Add Package Dependencies`. Paste the URL of the [ExecuTorch repo](https://github.com/pytorch/executorch) into the search bar and select it. Make sure to change the branch name to the desired ExecuTorch version in format "swiftpm-<version>", (e.g. "swiftpm-0.6.0"), or a branch name in format "swiftpm-<version>.<year_month_date>" (e.g. "swiftpm-0.6.0-20250501") for a nightly build on a specific date.
 
 ![](_static/img/swiftpm_xcode1.png)
 
@@ -58,7 +58,7 @@ let package = Package(
   ],
   dependencies: [
     // Use "swiftpm-<version>.<year_month_day>" branch name for a nightly build.
-    .package(url: "https://github.com/pytorch/executorch.git", branch: "swiftpm-0.5.0")
+    .package(url: "https://github.com/pytorch/executorch.git", branch: "swiftpm-0.6.0")
   ],
   targets: [
     .target(
@@ -97,7 +97,7 @@ xcode-select --install
 2. Clone ExecuTorch:
 
 ```bash
-git clone https://github.com/pytorch/executorch.git --depth 1 --recurse-submodules --shallow-submodules && cd executorch
+git clone -b release/0.6 https://github.com/pytorch/executorch.git && cd executorch
 ```
 
 3. Set up [Python](https://www.python.org/downloads/macos/) 3.10+ and activate a virtual environment:
@@ -106,15 +106,16 @@ git clone https://github.com/pytorch/executorch.git --depth 1 --recurse-submodul
 python3 -m venv .venv && source .venv/bin/activate && ./install_requirements.sh
 ```
 
-4. Install the required dependencies, including those needed for the backends like [Core ML](backends-coreml.md) or [MPS](backends-mps.md). Choose one:
+4. Install the required dependencies, including those needed for the backends like [Core ML](backends-coreml.md) or [MPS](backends-mps.md). Choose one, or both:
 
 ```bash
 # ExecuTorch with xnnpack and CoreML backend
-./install_executorch.sh --pybind xnnpack
+./backends/apple/coreml/scripts/install_requirements.sh
+./install_executorch.sh --pybind coreml xnnpack
 
-# Optional: ExecuTorch with xnnpack, CoreML, and MPS backend
+# ExecuTorch with xnnpack and MPS backend
 ./backends/apple/mps/install_requirements.sh
-./install_executorch.sh --pybind xnnpack mps
+./install_executorch.sh --pybind mps xnnpack
 ```
 
 5. Install [CMake](https://cmake.org):

@@ -21,23 +21,29 @@ Phone verified: MediaTek Dimensity 9300 (D9300) chip.
 ## Setup ExecuTorch
 In this section, we will need to set up the ExecuTorch repo first with Conda environment management. Make sure you have Conda available in your system (or follow the instructions to install it [here](https://anaconda.org/anaconda/conda)). The commands below are running on Linux (CentOS).
 
-Create a Conda environment
+Checkout ExecuTorch repo and sync submodules
+
 ```
-conda create -yn et_mtk python=3.10.0
-conda activate et_mtk
+git clone -b release/0.6 https://github.com/pytorch/executorch.git && cd executorch
 ```
 
-Checkout ExecuTorch repo and sync submodules
+Create either a Python virtual environment:
+
+```
+python3 -m venv .venv && source .venv/bin/activate && pip install --upgrade pip
 ```
-git clone https://github.com/pytorch/executorch.git
-cd executorch
-git submodule sync
-git submodule update --init
+
+Or a Conda environment:
+
+```
+conda create -n et_xnnpack python=3.10.0 && conda activate et_xnnpack
 ```
+
 Install dependencies
 ```
 ./install_executorch.sh
 ```
+
 ## Setup Environment Variables
 ### Download Buck2 and make executable
 * Download Buck2 from the official [Release Page](https://github.com/facebook/buck2/releases/tag/2024-02-01)

@@ -19,19 +19,24 @@ Phone verified: OnePlus 12, Samsung 24+, Samsung 23
 ## Setup ExecuTorch
 In this section, we will need to set up the ExecuTorch repo first with Conda environment management. Make sure you have Conda available in your system (or follow the instructions to install it [here](https://anaconda.org/anaconda/conda)). The commands below are running on Linux (CentOS).
 
-Create a Conda environment
+Checkout ExecuTorch repo and sync submodules
+
 ```
-conda create -n et_qnn python=3.10.0
-conda activate et_qnn
+git clone -b release/0.6 https://github.com/pytorch/executorch.git && cd executorch
 ```
 
-Checkout ExecuTorch repo and sync submodules
+Create either a Python virtual environment:
+
 ```
-git clone https://github.com/pytorch/executorch.git
-cd executorch
-git submodule sync
-git submodule update --init
+python3 -m venv .venv && source .venv/bin/activate && pip install --upgrade pip
 ```
+
+Or a Conda environment:
+
+```
+conda create -n et_xnnpack python=3.10.0 && conda activate et_xnnpack
+```
+
 Install dependencies
 ```
 ./install_executorch.sh
@@ -74,7 +79,7 @@ cmake --build cmake-out -j16 --target install --config Release
 ### Setup Llama Runner
 Next we need to build and compile the Llama runner. This is similar to the requirements for running Llama with XNNPACK.
 ```
-sh examples/models/llama/install_requirements.sh
+./examples/models/llama/install_requirements.sh
 
 cmake -DPYTHON_EXECUTABLE=python \
     -DCMAKE_INSTALL_PREFIX=cmake-out \

@@ -21,35 +21,34 @@ Phone verified: OnePlus 12, OnePlus 9 Pro. Samsung S23 (Llama only), Samsung S24
 ## Setup ExecuTorch
 In this section, we will need to set up the ExecuTorch repo first with Conda environment management. Make sure you have Conda available in your system (or follow the instructions to install it [here](https://anaconda.org/anaconda/conda)). The commands below are running on Linux (CentOS).
 
-Create a Conda environment
+Checkout ExecuTorch repo and sync submodules
+
 ```
-conda create -yn executorch python=3.10.0
-conda activate executorch
+git clone -b release/0.6 https://github.com/pytorch/executorch.git && cd executorch
 ```
 
-Checkout ExecuTorch repo and sync submodules
+Create either a Python virtual environment:
+
 ```
-git clone https://github.com/pytorch/executorch.git
-cd executorch
-git submodule sync
-git submodule update --init
+python3 -m venv .venv && source .venv/bin/activate && pip install --upgrade pip
 ```
-Install dependencies
+
+Or a Conda environment:
+
 ```
-./install_executorch.sh
+conda create -n et_xnnpack python=3.10.0 && conda activate et_xnnpack
 ```
 
-Optional: Use the --pybind flag to install with pybindings.
+Install dependencies
 ```
-./install_executorch.sh --pybind xnnpack
+./install_executorch.sh
 ```
 
-
 ## Prepare Models
 In this demo app, we support text-only inference with up-to-date Llama models and image reasoning inference with LLaVA 1.5.
 * You can request and download model weights for Llama through Meta official [website](https://llama.meta.com/).
 * For chat use-cases, download the instruct models instead of pretrained.
-* Run `examples/models/llama/install_requirements.sh` to install dependencies.
+* Run `./examples/models/llama/install_requirements.sh` to install dependencies.
 * Rename tokenizer for Llama3.x with command: `mv tokenizer.model tokenizer.bin`. We are updating the demo app to support tokenizer in original format directly.
 
 ### For Llama 3.2 1B and 3B SpinQuant models

@@ -806,7 +806,7 @@
 			isa = XCRemoteSwiftPackageReference;
 			repositoryURL = "https://github.com/pytorch/executorch";
 			requirement = {
-				branch = "swiftpm-0.5.0.20250317";
+				branch = "swiftpm-0.6.0";
 				kind = branch;
 			};
 		};

@@ -44,8 +44,7 @@ Follow the [Setting Up ExecuTorch](https://pytorch.org/executorch/stable/getting
 tutorial to configure the basic environment:
 
 ```bash
-git clone https://github.com/pytorch/executorch.git --depth 1 --recurse-submodules --shallow-submodules
-cd executorch
+git clone -b release/0.6 https://github.com/pytorch/executorch.git && cd executorch
 
 python3 -m venv .venv && source .venv/bin/activate
 

@@ -852,7 +852,7 @@
 			isa = XCRemoteSwiftPackageReference;
 			repositoryURL = "https://github.com/pytorch/executorch";
 			requirement = {
-				branch = "swiftpm-0.5.0.20250228";
+				branch = "swiftpm-0.6.0";
 				kind = branch;
 			};
 		};