diff --git a/README.md b/README.md index 8ab33305..93f41238 100644 --- a/README.md +++ b/README.md @@ -33,7 +33,11 @@ A high-performance [TensorFlow Lite](https://www.tensorflow.org/lite) library fo ``` This allows you to drop `.tflite` files into your app and swap them out at runtime without having to rebuild anything! 🔥 3. (Optional) If you want to enable the GPU Delegate, see ["Using GPU Delegates"](#using-gpu-delegates) down below. -4. Run your app (`yarn android` / `npx pod-install && yarn ios`) +4. Run your app: + - For Android: `yarn android` + - For iOS: + - If you're using Apple silicon (M1, M2, or M3), Since the current stable version of TensorFlow Lite doesn't support the `arm64` simulators, you'll need to use the following command to run the app on `x86_64` architecture: `npx pod-install && yarn ios --destination arch=x86_64` + - Otherwise, use this command: `npx pod-install && yarn ios` ## Usage diff --git a/react-native-fast-tflite.podspec b/react-native-fast-tflite.podspec index 2a4d852d..e2d21ae2 100644 --- a/react-native-fast-tflite.podspec +++ b/react-native-fast-tflite.podspec @@ -23,6 +23,7 @@ Pod::Spec.new do |s| s.source_files = "ios/**/*.{h,m,mm}", "cpp/**/*.{hpp,cpp,c,h}" s.pod_target_xcconfig = { + 'EXCLUDED_ARCHS[sdk=iphonesimulator*]' => 'arm64 i386', 'GCC_PREPROCESSOR_DEFINITIONS' => "$(inherited) FAST_TFLITE_ENABLE_CORE_ML=#{enableCoreMLDelegate}", 'CLANG_CXX_LANGUAGE_STANDARD' => 'c++17', }