Update README-wheel.md to document what's linked into pybindings (#3323)

* Stop linking MPS into the prebuilt pip wheel

We haven't tested this, and we'd prefer to have both MPS and Core ML
working. Remove it for now, putting macOS and Linux on equal footing.

* Update README-wheel.md to document what's linked into pybindings

Since pybindings can be built with many configurations, it's important
to tell users what's actually present in the wheel.

Author: dbort

README-wheel.md

@@ -4,6 +4,20 @@ standard on-device iOS and Android mobile deployments. One of the main goals for
 ExecuTorch is to enable wider customization and deployment capabilities of the
 PyTorch programs.
 
+The `executorch` pip package is in alpha.
+* Required python version: `==3.10`
+* Compatible systems: Linux x86_64, macOS aarch64
+
+The prebuilt `executorch.extension.pybindings.portable_lib` module included in
+this package provides a way to run ExecuTorch `.pte` files, with some
+restrictions:
+* Only [core ATen
+  operators](https://pytorch.org/executorch/stable/ir-ops-set-definition.html)
+  are linked into the prebuilt module
+* Only the [XNNPACK backend
+  delegate](https://pytorch.org/executorch/main/native-delegates-executorch-xnnpack-delegate.html)
+  is linked into the prebuilt module
+
 Please visit the [ExecuTorch website](https://pytorch.org/executorch/) for
 tutorials and documentation. Here are some starting points:
 * [Getting

build/packaging/env_var_script_m1.sh

@@ -21,8 +21,7 @@ CMAKE_ARGS="${CMAKE_ARGS} -DEXECUTORCH_BUILD_XNNPACK=ON"
 
 # When building for macOS, link additional backends into the pybindings runtime.
 
-# TODO(dbort): Core ML requires features only available in macOS 10.15, but the
+# TODO(dbort): Make these build properly in the CI environment.
 # build machine uses an older version.
 # CMAKE_ARGS="${CMAKE_ARGS} -DEXECUTORCH_BUILD_COREML=ON"
-
-CMAKE_ARGS="${CMAKE_ARGS} -DEXECUTORCH_BUILD_MPS=ON"
+# CMAKE_ARGS="${CMAKE_ARGS} -DEXECUTORCH_BUILD_MPS=ON"