Update setup and Readme

Author: cymbalrush

backends/apple/coreml/README.md

@@ -7,21 +7,18 @@ Core ML is an optimized framework for running machine learning models on Apple d
 ## Layout
 - `compiler/` : Lowers a module to Core ML backend.
 - `partition/`: Partitions a module fully or partially to Core ML backend.
-- `quantizer/`: Quantizes a module in Core ML favored scheme
+- `quantizer/`: Quantizes a module in Core ML favored scheme.
 - `scripts/` : Scripts for installing dependencies and running tests.
 - `runtime/`: Core ML delegate runtime implementation.
     - `inmemoryfs`: InMemory filesystem implementation used to serialize/de-serialize AOT blob.
     - `kvstore`: Persistent Key-Value store implementation.
     - `delegate`: Runtime implementation.
     - `include` : Public headers.
-    - `tests` :  Tests for Core ML delegate.
-    - `workspace` : Xcode workspace for tests.
+    - `sdk` : SDK implementation.
+    - `tests` :  Unit tests.
+    - `workspace` : Xcode workspace for the runtime.
 - `third-party/`: External dependencies.
 
-## Help & Improvements
-If you have problems or questions or have suggestions for ways to make
-implementation and testing better, please create an issue on [github](https://www.github.com/pytorch/executorch/issues).
-
 ## Partition and Delegation
 
 To delegate a Program to the **Core ML** backend, the client must call `to_backend` with the **CoreMLPartitioner**.
@@ -122,6 +119,10 @@ The `converted_graph` is the quantized torch model, and can be delegated to **Co
 
 ## Runtime
 
-To execute a **Core ML** delegated **Program**, the client must link to the `coremldelegate` library. Once linked there are no additional steps required, **ExecuTorch** when running the **Program** would call the **Core ML** runtime to execute the **Core ML** delegated part of the **Program**.
+To execute a Core ML delegated program, the application must link to the `coremldelegate` library. Once linked there are no additional steps required, ExecuTorch when running the program would call the Core ML runtime to execute the Core ML delegated part of the program.
 
 Please follow the instructions described in the [Core ML setup](/backends/apple/coreml/setup.md) to link the `coremldelegate` library.
+
+## Help & Improvements
+If you have problems or questions or have suggestions for ways to make
+implementation and testing better, please create an issue on [github](https://www.github.com/pytorch/executorch/issues).

backends/apple/coreml/setup.md

@@ -46,15 +46,15 @@ delegated_program_manager = edge_program_manager.to_backend(CoreMLPartitioner())
 xcode-select --install
 ```
 
-2. Build **Core ML** delegate. The following will create a `executorch.xcframework` in `cmake-out` directory.
+4. Build **Core ML** delegate. The following will create `executorch.xcframework` and `coreml_backend.xcframework` in the `cmake-out` directory.
 
 ```bash
 cd executorch
 ./build/build_apple_frameworks.sh --Release --coreml
 ```
-3. Open the project in Xcode, and drag the `executorch.xcframework` generated from Step 2 to Frameworks.
+5. Open the project in Xcode, and drag `executorch.xcframework` and `coreml_backend.xcframework` frameworks generated from Step 2 to Frameworks.
 
-4. Go to project Target’s Build Phases -  Link Binaries With Libraries, click the + sign, and add the following frameworks:
+6. Go to project Target’s Build Phases -  Link Binaries With Libraries, click the + sign, and add the following frameworks:
 
 ```
 executorch.xcframework
@@ -63,9 +63,9 @@ coreml_backend.xcframework
 
 5. Go to project Target’s Build Phases -  Link Binaries With Libraries, click the + sign, and add the following frameworks.
 ```
-- Accelerate.framework
-- CoreML.framework
-- libsqlite3.tbd
+Accelerate.framework
+CoreML.framework
+libsqlite3.tbd
 ```
 
 6. The target could now run a **Core ML** delegated **Program**.