diff --git a/docs/source/_static/img/swiftpm_xcode.mp4 b/docs/source/_static/img/swiftpm_xcode.mp4 index d2c0a2d85b1..bce5d5a8034 100644 Binary files a/docs/source/_static/img/swiftpm_xcode.mp4 and b/docs/source/_static/img/swiftpm_xcode.mp4 differ diff --git a/docs/source/_static/img/swiftpm_xcode2.png b/docs/source/_static/img/swiftpm_xcode2.png index 10f8c19470d..bb7c5f4dc56 100644 Binary files a/docs/source/_static/img/swiftpm_xcode2.png and b/docs/source/_static/img/swiftpm_xcode2.png differ diff --git a/docs/source/getting-started.md b/docs/source/getting-started.md index 43036cc0e8d..69a7da8ce18 100644 --- a/docs/source/getting-started.md +++ b/docs/source/getting-started.md @@ -158,7 +158,7 @@ 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-0.6.0”). The ExecuTorch dependency can also be added to the package file manually. See [Using ExecuTorch on iOS](using-executorch-ios.md) for more information. +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 dependency rule to a branch named for the desired ExecuTorch version (e.g., `swiftpm-1.0.0`). 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. diff --git a/docs/source/using-executorch-ios.md b/docs/source/using-executorch-ios.md index 78d22080d8d..57bb60ebb61 100644 --- a/docs/source/using-executorch-ios.md +++ b/docs/source/using-executorch-ios.md @@ -28,11 +28,11 @@ 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-", (e.g. "swiftpm-1.0.0"), or a branch name in format "swiftpm-." (e.g. "swiftpm-1.1.0-20251101") for a [nightly build](https://ossci-ios.s3.amazonaws.com/list.html) 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. Change the dependency rule to a branch named for the desired ExecuTorch version (e.g., `swiftpm-1.0.0`), or use a branch name in the format `swiftpm-.` for a [nightly build](https://ossci-ios.s3.amazonaws.com/list.html) on a specific date (e.g., `swiftpm-1.1.0.20251101`). ![](_static/img/swiftpm_xcode1.png) -Then select which ExecuTorch framework should link against which target. +Then select the ExecuTorch products that your app needs. For a simple app using the XNNPACK backend, link the app target against `executorch`, `backend_xnnpack`, and `kernels_optimized`. The `executorch` product provides the core runtime; for Core ML, MPS, or other execution paths, choose the matching backend and kernel products from the product list above. ![](_static/img/swiftpm_xcode2.png)