Update base for Update on "Update pytorch nightly pin to 03/13"

## Context

Updating PyTorch nightly pin to 03/13 to capture dynamic shape support in ATen Vulkan (pytorch/pytorch#121598).

Previous upate was to 03/12 (#2370) so this should not be a risky change. Also, according to PyTorch nightly HUD (https://hud.pytorch.org/hud/pytorch/pytorch/nightly) this 03/13 nightly is all green while 03/12 nightly had some failures.

Differential Revision: [D54870270](https://our.internmc.facebook.com/intern/diff/D54870270)

[ghstack-poisoned]

Author: SS-JIA

.github/workflows/app-build.yml

@@ -0,0 +1,92 @@
+name: Apple
+
+on:
+  push:
+    branches:
+      - main
+      - release/*
+  pull_request:
+    paths:
+      - .ci/docker/**
+      - .github/workflows/app-build.yml
+      - install_requirements.sh
+      - backends/apple/**
+      - build/build_apple_frameworks.sh
+      - build/create_frameworks.sh
+      - build/test_ios_ci.sh
+      - examples/demo-apps/**
+      - extension/apple/**
+      - extension/module/**
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}-${{ github.event_name == 'workflow_dispatch' }}-${{ github.event_name == 'schedule' }}
+  cancel-in-progress: true
+
+jobs:
+  test-demo-ios:
+    name: test-demo-ios
+    uses: pytorch/test-infra/.github/workflows/macos_job.yml@main
+    with:
+      runner: macos-latest-xlarge
+      python-version: '3.11'
+      submodules: 'true'
+      ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
+      timeout: 90
+      script: |
+        WORKSPACE=$(pwd)
+        pushd "${WORKSPACE}/pytorch/executorch"
+        BUILD_TOOL=cmake
+
+        .ci/scripts/setup-conda.sh
+
+        # Setup MacOS dependencies as there is no Docker support on MacOS atm
+        GITHUB_RUNNER=1 PYTHON_EXECUTABLE=python ${CONDA_RUN} --no-capture-output \
+        .ci/scripts/setup-macos.sh "${BUILD_TOOL}"
+
+        # Build and test iOS Demo App
+        PYTHON_EXECUTABLE=python ${CONDA_RUN} --no-capture-output \
+        build/test_ios_ci.sh
+
+        popd
+
+  build-frameworks-ios:
+    name: build-frameworks-ios
+    uses: pytorch/test-infra/.github/workflows/macos_job.yml@main
+    with:
+      runner: macos-latest-xlarge
+      python-version: '3.11'
+      submodules: 'true'
+      ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
+      upload-artifact: executorch.zip
+      timeout: 90
+      script: |
+        WORKSPACE=$(pwd)
+        pushd "${WORKSPACE}/pytorch/executorch"
+        BUILD_TOOL=cmake
+        VERSION="0.1.0"
+        OUTPUT="executorch-${VERSION}"
+
+        .ci/scripts/setup-conda.sh
+
+        # Setup MacOS dependencies as there is no Docker support on MacOS atm
+        GITHUB_RUNNER=1 PYTHON_EXECUTABLE=python ${CONDA_RUN} --no-capture-output \
+        .ci/scripts/setup-macos.sh "${BUILD_TOOL}"
+
+        # Install CoreML Backend Requirements
+        PYTHON_EXECUTABLE=python ${CONDA_RUN} --no-capture-output \
+        backends/apple/coreml/scripts/install_requirements.sh
+
+        # Install MPS Backend Requirements
+        PYTHON_EXECUTABLE=python ${CONDA_RUN} --no-capture-output \
+        backends/apple/mps/install_requirements.sh
+
+        # Build iOS Frameworks
+        PYTHON_EXECUTABLE=python ${CONDA_RUN} --no-capture-output \
+        build/build_apple_frameworks.sh --output="${OUTPUT}" --coreml --mps --portable --xnnpack
+
+        # Bundle iOS Frameworks
+        cp LICENSE "${OUTPUT}"
+        zip -r "${RUNNER_TEMP}/artifacts/${OUTPUT}.zip" "${OUTPUT}"
+
+        popd

.github/workflows/apple.yml

@@ -2,4 +2,6 @@
 #
 # Please refer to the license found in the LICENSE file in the root directory of the source tree.
 
-from coremltools.optimize.torch.quantization._coreml_quantizer import CoreMLQuantizer
+from coremltools.optimize.torch.quantization._coreml_quantizer import (  # noqa: FLAKE8 F401
+    CoreMLQuantizer,
+)

backends/apple/coreml/quantizer/coreml_quantizer.py

@@ -23,8 +23,8 @@ cd "$EXECUTORCH_ROOT_PATH"
 MODELS=("add" "mul" "mv3")
 for MODEL in "${MODELS[@]}"
 do
-  # TODO: Don't use the script in examples directory. 
-  python3 -m examples.apple.coreml.scripts.export_and_delegate --model_name "$MODEL" --save_processed_bytes
+  # TODO: Don't use the script in examples directory.
+  python3 -m examples.apple.coreml.scripts.export --model_name "$MODEL" --save_processed_bytes
   mv -f "$MODEL""_coreml_all.pte" "$COREML_DIR_PATH/runtime/test/models"
   mv -f "$MODEL""_coreml_all.bin" "$COREML_DIR_PATH/runtime/test/models"
 done

backends/apple/coreml/scripts/generate_test_models.sh

@@ -11,18 +11,18 @@ This is a tutorial for setting up the Core ML backend.
 ```
 cd executorch
 
-./backends/apple/coreml/scripts/install_requirements.sh   
+./backends/apple/coreml/scripts/install_requirements.sh
 
-``` 
+```
 
-3. Run the example script to validate that the **Core ML** backend is set up correctly. 
+3. Run the example script to validate that the **Core ML** backend is set up correctly.
 
 ```
 cd executorch
 
 # Saves add_coreml_all.pte in the current directory if successful.
 
-python3 -m examples.apple.coreml.scripts.export_and_delegate --model_name add 
+python3 -m examples.apple.coreml.scripts.export --model_name add
 
 ```
 
@@ -66,6 +66,6 @@ coreml_backend.xcframework
 - Accelerate.framework
 - CoreML.framework
 - libsqlite3.tbd
-``` 
+```
 
-6. The target could now run a **Core ML** delegated **Program**. 
+6. The target could now run a **Core ML** delegated **Program**.

backends/apple/coreml/setup.md

@@ -2,21 +2,26 @@
 #
 # Please refer to the license found in the LICENSE file in the root directory of the source tree.
 
+from typing import Tuple
+
 import numpy as np
 import pytest
-from typing import Tuple
 
 import torch
-from torch._export import capture_pre_autograd_graph
-from torch.ao.quantization.quantize_pt2e import convert_pt2e, prepare_pt2e, prepare_qat_pt2e
-
-from executorch.backends.apple.coreml.quantizer.coreml_quantizer import CoreMLQuantizer
 
 from coremltools.optimize.torch.quantization.quantization_config import (
     LinearQuantizerConfig,
     QuantizationScheme,
 )
 
+from executorch.backends.apple.coreml.quantizer.coreml_quantizer import CoreMLQuantizer
+from torch._export import capture_pre_autograd_graph
+from torch.ao.quantization.quantize_pt2e import (
+    convert_pt2e,
+    prepare_pt2e,
+    prepare_qat_pt2e,
+)
+
 
 class TestCoreMLQuantizer:
     @staticmethod