Update install script and building from source docs

README.md

@@ -19,7 +19,7 @@ It supports a wide range of models including LLMs (Large Language Models), CV (C
 Platform Support:
 - Operating Systems:
   - iOS
-  - Mac
+  - MacOS (ARM64)
   - Android
   - Linux
   - Microcontrollers

docs/source/backends-xnnpack.md

@@ -14,7 +14,7 @@ The XNNPACK delegate is the ExecuTorch solution for CPU execution on mobile CPUs
 - ARM64 on Android, iOS, macOS, Linux, and Windows.
 - ARMv7 (with NEON) on Android.
 - ARMv6 (with VFPv2) on Linux.
-- x86 and x86-64 (up to AVX512) on Windows, Linux, macOS, Android, and iOS simulator.
+- x86 and x86-64 (up to AVX512) on Windows, Linux, Android.
 
 ## Development Requirements
 

docs/source/getting-started.md

@@ -10,8 +10,9 @@ The following are required to install the ExecuTorch host libraries, needed to e
 
 - Python 3.10 - 3.12
 - g++ version 7 or higher, clang++ version 5 or higher, or another C++17-compatible toolchain.
-- Linux or MacOS operating system (Arm or x86).
-  - Windows is supported via WSL.
+- Linux (x86_64 or ARM64) or macOS (ARM64).
+    - Intel-based macOS systems require building PyTorch from source (see [Building From Source](using-executorch-building-from-source.md) for instructions).
+    - Windows is supported via WSL.
 
 ## Installation
 To use ExecuTorch, you will need to install both the Python package and the appropriate platform-specific runtime libraries. Pip is the recommended way to install the ExecuTorch python package.

docs/source/using-executorch-building-from-source.md

@@ -16,7 +16,7 @@ Linux (x86_64)
 - Ubuntu 20.04.6 LTS+
 - RHEL 8+
 
-macOS (x86_64/M1/M2)
+macOS (x86_64/ARM64)
 - Big Sur (11.0)+
 
 Windows (x86_64)
@@ -56,13 +56,21 @@ Or alternatively, [install conda on your machine](https://conda.io/projects/cond
    conda create -yn executorch python=3.10.0 && conda activate executorch
    ```
 
-## Install ExecuTorch pip package from Source
+## Install ExecuTorch pip package from source
    ```bash
    # Install ExecuTorch pip package and its dependencies, as well as
    # development tools like CMake.
    # If developing on a Mac, make sure to install the Xcode Command Line Tools first.
+   # Intel-based macOS systems require building PyTorch, Torchvision, and Torchaudio from source (see below)
    ./install_executorch.sh
    ```
+
+  Use the [`--use-pt-pinned-commit` flag](https://github.com/pytorch/executorch/blob/main/install_executorch.sh) to install Executorch with an existing PyTorch build.  
+  See the [PyTorch instructions](https://github.com/pytorch/pytorch#installation) on how to build PyTorch from source.
+
+   ```bash
+   ./install_executorch.sh --use-pt-pinned-commit
+   ```
 
    Use the [`--pybind` flag](https://github.com/pytorch/executorch/blob/main/install_executorch.sh#L26-L29) to install with pybindings and dependencies for other backends.
    ```bash

docs/source/using-executorch-ios.md

@@ -4,7 +4,7 @@ ExecuTorch supports both iOS and macOS via Objective-C, Swift, and C++. ExecuTor
 
 ## Integration
 
-The ExecuTorch Runtime for iOS and macOS is distributed as a collection of prebuilt [.xcframework](https://developer.apple.com/documentation/xcode/creating-a-multi-platform-binary-framework-bundle) binary targets. These targets are compatible with both iOS and macOS devices and simulators and are available in both release and debug modes:
+The ExecuTorch Runtime for iOS and macOS (ARM64) is distributed as a collection of prebuilt [.xcframework](https://developer.apple.com/documentation/xcode/creating-a-multi-platform-binary-framework-bundle) binary targets. These targets are compatible with both iOS and macOS devices and simulators and are available in both release and debug modes:
 
 * `executorch` - Main Runtime components
 * `backend_coreml` - Core ML backend
@@ -118,6 +118,13 @@ python3 -m venv .venv && source .venv/bin/activate && pip install --upgrade pip
 ./backends/apple/mps/install_requirements.sh
 ```
 
+- **Intel-based macOS** systems require building PyTorch, Torchvision, and Torchaudio from source:  
+  - Use the [`--use-pt-pinned-commit` flag](https://github.com/pytorch/executorch/blob/main/install_requirements.sh) to install Executorch with an existing PyTorch build.  
+    See the [PyTorch instructions](https://github.com/pytorch/pytorch#installation) on how to build PyTorch from source.
+    ```bash
+    ./install_requirements.sh --use-pt-pinned-commit
+    ```
+
 5. Install [CMake](https://cmake.org):
 
 Download the macOS binary distribution from the [CMake website](https://cmake.org/download), open the `.dmg` file, move `CMake.app` to the `/Applications` directory, and then run the following command to install the CMake command-line tools:

install_executorch.py

@@ -196,9 +196,6 @@ def _list_pybind_defines(args) -> Tuple[bool, List[str]]:
 
 
 def main(args):
-    if not python_is_compatible():
-        sys.exit(1)
-
     parser = build_args_parser()
     args = parser.parse_args()
 

install_requirements.py

@@ -75,45 +75,69 @@ def python_is_compatible():
 
 
 def install_requirements(use_pytorch_nightly):
+    is_intel_mac = is_intel_mac_os()
+
+    # Skip pip install on Intel macOS if using nightly.
+    if use_pytorch_nightly and is_intel_mac:
+        print(
+            "ERROR: Prebuilt PyTorch wheels are no longer available for Intel-based macOS.\n"
+            "Please build from source by following https://docs.pytorch.org/executorch/main/using-executorch-building-from-source.html",
+            file=sys.stderr,
+        )
+        sys.exit(1)
+
     # pip packages needed by exir.
     EXIR_REQUIREMENTS = [
         # Setting use_pytorch_nightly to false to test the pinned PyTorch commit. Note
         # that we don't need to set any version number there because they have already
         # been installed on CI before this step, so pip won't reinstall them
-        f"torch==2.8.0.{NIGHTLY_VERSION}" if use_pytorch_nightly else "torch",
-        (
+        f"torch==2.8.0.{NIGHTLY_VERSION}" if use_pytorch_nightly else "torch"
+    ]
+
+    EXAMPLES_REQUIREMENTS = []
+
+    # Only pip install torchvision and torchaudio if not building PyTorch from source on Intel macOS,
+    # to avoid having incompatible prebuilt wheels from PyPI installed.
+    if not is_intel_mac:
+        EXIR_REQUIREMENTS.append(
             f"torchvision==0.22.0.{NIGHTLY_VERSION}"
             if use_pytorch_nightly
             else "torchvision"
-        ),  # For testing.
-    ]
+        )  # For testing.
 
-    EXAMPLES_REQUIREMENTS = [
-        f"torchaudio==2.6.0.{NIGHTLY_VERSION}" if use_pytorch_nightly else "torchaudio",
-    ]
+        EXAMPLES_REQUIREMENTS = [
+            (
+                f"torchaudio==2.6.0.{NIGHTLY_VERSION}"
+                if use_pytorch_nightly
+                else "torchaudio"
+            )
+        ]
 
     # Assemble the list of requirements to actually install.
     # TODO: Add options for reducing the number of requirements.
     REQUIREMENTS_TO_INSTALL = EXIR_REQUIREMENTS + EXAMPLES_REQUIREMENTS
 
     # Install the requirements. `--extra-index-url` tells pip to look for package
     # versions on the provided URL if they aren't available on the default URL.
-    subprocess.run(
-        [
-            sys.executable,
-            "-m",
-            "pip",
-            "install",
-            "-r",
-            "requirements-examples.txt",
-            "-r",
-            "requirements-dev.txt",
-            *REQUIREMENTS_TO_INSTALL,
-            "--extra-index-url",
-            TORCH_NIGHTLY_URL,
-        ],
-        check=True,
-    )
+    pip_args = [
+        sys.executable,
+        "-m",
+        "pip",
+        "install",
+        "-r",
+        "requirements-examples.txt",
+        "-r",
+        "requirements-dev.txt",
+        *REQUIREMENTS_TO_INSTALL,
+        "--extra-index-url",
+        TORCH_NIGHTLY_URL,
+    ]
+
+    # If pytorch is built from source add no-deps flag to stop dependencies from changing torch version
+    if not use_pytorch_nightly:
+        pip_args.append("--no-deps")
+
+    subprocess.run(pip_args, check=True)
 
     LOCAL_REQUIREMENTS = [
         "third-party/ao",  # We need the latest kernels for fast iteration, so not relying on pypi.
@@ -139,6 +163,17 @@ def install_requirements(use_pytorch_nightly):
     )
 
 
+# Prebuilt wheels for Intel macOS are no longer available on PyPI; users must compile from source.
+# PyTorch stopped building macOS x86_64 binaries since version 2.3.0 (January 2024).
+def is_intel_mac_os():
+    # Returns True if running on Intel macOS
+    return platform.system().lower() == "darwin" and platform.machine().lower() in (
+        "x86",
+        "x86_64",
+        "i386",
+    )
+
+
 def main(args):
     parser = argparse.ArgumentParser()
     parser.add_argument(