Skip to content

Minor doc fixes #15336

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 22, 2025
Merged

Minor doc fixes #15336

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs/source/getting-started.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ The following are required to install the ExecuTorch host libraries, needed to e
- g++ version 7 or higher, clang++ version 5 or higher, or another C++17-compatible toolchain.
- Linux (x86_64 or ARM64), macOS (ARM64), or Windows (x86_64).
- Intel-based macOS systems require building PyTorch from source (see [Building From Source](using-executorch-building-from-source.md) for instructions).
- On Windows, Visual Studio 2022 or later. Clang build tools are needed to build from source.
- On Windows, Visual Studio 2022 or later.
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Removing the build from source callout as it's covered in the building from source section. We do still need VS 2022 because torch.export does C++ compilation (via MSVC) in strict mode.


## 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.
Expand Down
5 changes: 3 additions & 2 deletions docs/source/using-executorch-building-from-source.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,7 +83,7 @@ portability details.
CMAKE_ARGS="-DEXECUTORCH_BUILD_MPS=ON" ./install_executorch.sh
```

## Verify the Build
### Verify the Build

To verify that the Python components are installed correctly, run the following command. This will create a file named mv2_xnnpack_fp32.pte in the current directory for the MobileNet V2 model with the XNNPACK backend. If it completes without error, the ExecuTorch Python components are installed successfully.
```bash
Expand Down Expand Up @@ -162,7 +162,8 @@ ExecuTorch provides fine-grained control over what is built, as described in [Bu

Preset values for common scenarios are listed below. Using a platform preset is recommended to avoid needing to specify many fine-grained build options.

* `android` - Build featuers and backends common for Android targets.
* `android-arm64-v8a` - Build features and backends common for arm64-v8a Android targets.
* `android-x86_64` - Build features and backends common for x86_64 Android targets.
* `arm-baremetal` - Build for bare-metal ARM targets.
* `ios` - Build features and backends common for iOS targets.
* `macos` - Build features and backends common for Mac targets.
Expand Down
Loading