Update base for Update on "Use unlifted export pass to tag delegated constants"

Use the unlifted pass to tag constants for delegates.

Implications:
- Tagging must happen on the unlifted ep.module(), before going into to_edge_transform_and_lower/to_edge.

Why?
- The unlifted graph contains constants in getattr nodes, which is a convenient way to isolate constants.
- After going into to_edge_transform_and_lower/to_edge, transforms happen on the graph_module, which is lifted.
- The lifted graph requires the ep graph signature to differentiate constants via the `is_param` function. However, in to_edge.transform, we do not have access to the ep. Baking the ep as an argument via partial function doesn't work, as the ep from earlier may be outdated. This means we are comparing an older ep to a newer graph_module, which may not have corresponding graph signatures etc.

Differential Revision: [D79736684](https://our.internmc.facebook.com/intern/diff/D79736684/)

[ghstack-poisoned]

Author: lucylq

.ci/scripts/setup-vulkan-linux-deps.sh

@@ -23,6 +23,7 @@ install_swiftshader() {
 
   export VK_ICD_FILENAMES="${_swiftshader_dir}/swiftshader/build/Linux/vk_swiftshader_icd.json"
   export LD_LIBRARY_PATH="${_swiftshader_dir}/swiftshader/build/Linux/"
+  export ETVK_USING_SWIFTSHADER=1
 }
 
 install_vulkan_sdk() {

.github/workflows/build-presets.yml

@@ -6,8 +6,6 @@ on:
     branches:
       - main
       - release/*
-    paths:
-      - .github/workflows/build-presets.yml
   workflow_dispatch:
 
 concurrency:

.github/workflows/pull.yml

@@ -801,6 +801,8 @@ jobs:
       id-token: write
       contents: read
     strategy:
+      matrix:
+        enable-etdump: ['', '--enable-etdump']
       fail-fast: false
     with:
       runner: linux.2xlarge
@@ -820,7 +822,7 @@ jobs:
         source .ci/scripts/setup-emscripten.sh
 
         # Test selective build
-        bash scripts/build_wasm_tests.sh
+        bash scripts/build_wasm_tests.sh ${{ matrix.enable-etdump }}
 
         # Install Jest
         cd cmake-out-wasm/extension/wasm/test
@@ -862,6 +864,43 @@ jobs:
         PYTHON_EXECUTABLE=python bash examples/nxp/run_aot_example.sh
 
 
+  test-vulkan-models-linux:
+    name: test-vulkan-models-linux
+    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    permissions:
+      id-token: write
+      contents: read
+    with:
+      runner: linux.2xlarge
+      docker-image: ci-image:executorch-ubuntu-22.04-clang12
+      submodules: 'recursive'
+      ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
+      timeout: 90
+      script: |
+        set -eux
+
+        # The generic Linux job chooses to use base env, not the one setup by the image
+        CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
+        conda activate "${CONDA_ENV}"
+
+        # Setup swiftshader and Vulkan SDK which are required to build the Vulkan delegate
+        source .ci/scripts/setup-vulkan-linux-deps.sh
+
+        # Setup python
+        PYTHON_EXECUTABLE=python \
+        CMAKE_ARGS="-DEXECUTORCH_BUILD_VULKAN=ON" \
+        .ci/scripts/setup-linux.sh --build-tool "cmake"
+
+        PYTHON_EXECUTABLE=python bash backends/vulkan/test/scripts/test_model.sh --build
+
+        # Test models serially
+        models="mv2 mv3 edsr resnet18 resnet50 dl3"
+        for model in $models; do
+          python -m examples.vulkan.export --model_name=$model --test
+        done
+
+
+
   nxp-build-test:
     name: nxp-build-test
     uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main

.github/workflows/trunk.yml

@@ -288,6 +288,7 @@ jobs:
           - test_arm_baremetal: test_models_tosa
           - test_arm_baremetal: test_models_ethos-u55
           - test_arm_baremetal: test_models_ethos-u85
+          - test_arm_baremetal: test_smaller_stories_llama
       fail-fast: false
     with:
       runner: linux.2xlarge.memory

.gitignore

@@ -24,6 +24,7 @@ pip-out/
 # Any exported models and profiling outputs
 *.bin
 *.model
+*.etdump
 tokenizer.json
 *.pte
 *.ptd
@@ -58,6 +59,7 @@ xcuserdata/
 /include/
 /share/
 /version.py
+*.csv
 
 # Android
 *.aar

.lintrunner.toml

@@ -136,6 +136,36 @@ init_command = [
     '--requirement=requirements-lintrunner.txt',
 ]
 
+[[linter]]
+code = 'CMAKEFORMAT'
+include_patterns = [
+    "**/*.cmake",
+    "**/*.cmake.in",
+    "**/CMakeLists.txt",
+]
+exclude_patterns = [
+    'third-party/**',
+    '**/third-party/**',
+]
+command = [
+    'python',
+    '-m',
+    'lintrunner_adapters',
+    'run',
+    'cmake_format_linter',
+    '--',
+    '@{{PATHSFILE}}',
+]
+init_command = [
+    'python',
+    '-m',
+    'lintrunner_adapters',
+    'run',
+    'pip_init',
+    '--dry-run={{DRYRUN}}',
+    '--requirement=requirements-lintrunner.txt',
+]
+
 [[linter]]
 code = 'ETCAPITAL'
 include_patterns = [

CMakeLists.txt

@@ -284,15 +284,19 @@ if(EXECUTORCH_BUILD_KERNELS_TORCHAO)
   set(TORCHAO_BUILD_CPU_AARCH64 ON)
   set(TORCHAO_ENABLE_ARM_NEON_DOT ON)
 
-  list(APPEND TORCHAO_INCLUDE_DIRS
+  list(
+    APPEND
+    TORCHAO_INCLUDE_DIRS
     ${EXECUTORCH_ROOT}/backends/xnnpack/third-party/pthreadpool/include
     ${EXECUTORCH_ROOT}/backends/xnnpack/third-party/cpuinfo/include
     ${EXECUTORCH_ROOT}/third-party/ao
   )
 
   set(EXECUTORCH_INCLUDE_DIRS ${TORCHAO_INCLUDE_DIRS})
 
-  add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/third-party/ao/torchao/experimental)
+  add_subdirectory(
+    ${CMAKE_CURRENT_SOURCE_DIR}/third-party/ao/torchao/experimental
+  )
   executorch_target_link_options_shared_lib(torchao_ops_executorch)
   list(APPEND _executorch_kernels torchao_ops_executorch)
 endif()
@@ -759,6 +763,10 @@ if(EXECUTORCH_BUILD_PYBIND)
     list(APPEND _dep_libs xnnpack_backend XNNPACK xnnpack-microkernels-prod)
   endif()
 
+  if(EXECUTORCH_BUILD_VULKAN)
+    list(APPEND _dep_libs vulkan_backend)
+  endif()
+
   # compile options for pybind
   set(_pybind_compile_options -Wno-deprecated-declarations -fPIC -frtti
                               -fexceptions

backends/apple/coreml/TARGETS

@@ -120,6 +120,7 @@ runtime.python_test(
         "test/*.py",
     ]),
     deps = [
+        "fbsource//third-party/pypi/coremltools:coremltools",
         "fbsource//third-party/pypi/pytest:pytest",
         ":partitioner",
         ":quantizer",