Update (base update)

[ghstack-poisoned]

Author: Gasoonjia

.ci/scripts/test-rocm-aoti.sh

@@ -24,10 +24,10 @@ export TORCHINDUCTOR_COMPILE_THREADS=1
 
 read -r TORCH_VERSION TORCHAO_VERSION < <(
   python - <<'PY'
-from install_requirements import TORCHAO_NIGHTLY_VERSION
+from install_requirements import ROCM_TORCHAO_NIGHTLY_VERSION
 from torch_pin import TORCH_VERSION
 
-print(TORCH_VERSION, TORCHAO_NIGHTLY_VERSION)
+print(TORCH_VERSION, ROCM_TORCHAO_NIGHTLY_VERSION)
 PY
 )
 # TorchAO ROCm wheels are not exposed by the per-version pip index.

.ci/scripts/test-rocm-voxtral.sh

@@ -35,10 +35,10 @@ export HF_TOKEN
 
 read -r TORCH_VERSION TORCHAO_VERSION < <(
   python - <<'PY'
-from install_requirements import TORCHAO_NIGHTLY_VERSION
+from install_requirements import ROCM_TORCHAO_NIGHTLY_VERSION
 from torch_pin import TORCH_VERSION
 
-print(TORCH_VERSION, TORCHAO_NIGHTLY_VERSION)
+print(TORCH_VERSION, ROCM_TORCHAO_NIGHTLY_VERSION)
 PY
 )
 # TorchAO ROCm wheels are not exposed by the per-version pip index.
@@ -48,7 +48,22 @@ python -m pip install "torch==${TORCH_VERSION}" \
   --index-url "${PYTORCH_ROCM_INDEX}"
 python -m pip install -r requirements-dev.txt \
   "${TORCHAO_WHEEL}"
-python -m pip install --editable . --no-build-isolation
+# ExecuTorch requires torchao>=TORCHAO_NIGHTLY_VERSION, which has no ROCm build, so
+# install its other dependencies separately to keep the ROCm TorchAO wheel in place.
+python -m pip install --editable . --no-build-isolation --no-deps
+python - <<'PY' >"${VOXTRAL_CI_TMPDIR}/executorch-deps.txt"
+from importlib.metadata import requires
+
+from packaging.requirements import Requirement
+
+for spec in requires("executorch") or []:
+    req = Requirement(spec)
+    if req.name == "torchao":
+        continue
+    if req.marker is None or req.marker.evaluate({"extra": ""}):
+        print(spec)
+PY
+python -m pip install -r "${VOXTRAL_CI_TMPDIR}/executorch-deps.txt"
 
 if ! command -v conda >/dev/null; then
   echo "The ROCm CI image must provide conda for its runtime libraries"

.github/pytorch-probot.yml

@@ -3,6 +3,7 @@ tracking_issue: 7679
 ciflow_push_tags:
 - ciflow/android
 - ciflow/apple
+- ciflow/coreai
 - ciflow/cuda
 - ciflow/cuda-perf
 - ciflow/docker

.github/workflows/android-release-artifacts.yml

@@ -162,7 +162,8 @@ jobs:
 
         if [[ "$FLAVOR" == "qnn" || "$FLAVOR" == "all" ]]; then
           PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
-          PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh
+          # build_android_library.sh builds the QNN runtime included in the AAR;
+          # the host-only PyQnnManagerAdaptor is not part of this artifact.
           export EXECUTORCH_BUILD_QNN=ON
           source backends/qualcomm/scripts/qnn_config.sh
           export QNN_SDK_ROOT="/tmp/qnn/${QNN_VERSION}"

.github/workflows/coreai.yml

@@ -0,0 +1,68 @@
+name: Core AI
+
+on:
+  push:
+    branches:
+      - main
+      - release/*
+    tags:
+      - ciflow/coreai/*
+  pull_request:
+    paths:
+      - .github/workflows/coreai.yml
+      - backends/apple/coreai/**
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref_name }}-${{ github.ref_type == 'branch' && github.sha }}-${{ github.event_name == 'workflow_dispatch' }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+
+jobs:
+  run-decision:
+    name: CI run decision
+    uses: ./.github/workflows/_ci-run-decision.yml
+
+  test-coreai:
+    needs: run-decision
+    if: |
+      github.event_name == 'pull_request' ||
+      needs.run-decision.outputs.is-full-run == 'true'
+    uses: pytorch/test-infra/.github/workflows/macos_job.yml@main
+    with:
+      default-packages: ""
+      job-name: test-coreai
+      # GitHub-hosted macOS 27 with Xcode 27 (public preview).
+      runner: xcode-27
+      # coreai-opt supports Python < 3.14.
+      python-version: "3.12"
+      submodules: recursive
+      ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
+      timeout: 90
+      script: |
+        set -eux
+
+        echo "::group::Toolchain"
+        sw_vers
+        xcodebuild -version
+        xcrun --show-sdk-version
+        echo "::endgroup::"
+
+        echo "::group::Install the Metal Toolchain"
+        # coreai-build ships in the Metal Toolchain; without it the AOT compile
+        # tests skip.
+        xcodebuild -downloadComponent MetalToolchain
+        xcrun --find coreai-build
+        echo "::endgroup::"
+
+        echo "::group::Install ExecuTorch and Core AI requirements"
+        ${CONDA_RUN} python install_executorch.py --editable > /dev/null
+        ${CONDA_RUN} pip install -r backends/apple/coreai/requirements.txt
+        ${CONDA_RUN} pip list
+        echo "::endgroup::"
+
+        echo "::group::Run Core AI export tests"
+        ${CONDA_RUN} python -m pytest backends/apple/coreai
+        echo "::endgroup::"

.github/workflows/pull.yml

@@ -871,6 +871,24 @@ jobs:
 
         .ci/scripts/setup-arm-baremetal-tools.sh --disable-ethos-u-deps
 
+        if [[ "${{ matrix.test_arm_backend }}" == "test_pytest_ops_no_target" ]]; then
+          for backend in vgf u55 u85; do
+            python backends/arm/scripts/docgen/generate_op_support.py \
+              --backend "$backend" --check || exit 1
+
+            python backends/arm/scripts/docgen/generate_op_support.py \
+              --backend "$backend" || exit 1
+          done
+
+          git diff --exit-code -- \
+            docs/source/backends/arm-vgf/VGF_op_support.md \
+            docs/source/backends/arm-ethos-u/U55_op_support.md \
+            docs/source/backends/arm-ethos-u/U85_op_support.md || {
+              echo "::error::Operator support documentation is outdated. Regenerate it and commit the changes."
+              exit 1
+            }
+        fi
+
         ARM_TEST=${{ matrix.test_arm_backend }}
 
         # Test test_arm_backend.sh with test
@@ -887,6 +905,7 @@ jobs:
         include:
           - test_arm_backend: test_pytest_ops_vkml
           - test_arm_backend: test_ootb_tests_vgf
+          - test_arm_backend: test_runtime_vgf
       fail-fast: false
     with:
       runner: linux.2xlarge.memory

.github/workflows/trunk.yml

@@ -328,6 +328,7 @@ jobs:
           - test_arm_backend: test_pytest_models_vkml
           - test_arm_backend: test_run_vkml
           - test_arm_backend: test_ootb_tests_vgf
+          - test_arm_backend: test_runtime_vgf
           - test_arm_backend: test_smaller_stories_llama_vkml
       fail-fast: false
     with:

.gitignore

@@ -18,6 +18,7 @@ cmake-ios-out/
 cmake-out*
 cmake-out-android/
 backends/webgpu/third-party/
+backends/arm/test/models/neural_graphics_data/
 build-android/
 build-x86/
 build-direct/

backends/apple/__init__.py

@@ -33,21 +33,15 @@ Legitimate non-prose dashes are fine: CLI flags (`--platform`,
 
 ## Running the tests
 
-Run the whole backend suite (both `test/` and `passes/test/`) with the helper
-script, from inside the Core AI conda env:
+Run the whole backend suite (both `test/` and `passes/test/`) from the
+repository root, in an env with ExecuTorch installed in editable mode and
+`backends/apple/coreai/requirements.txt` installed:
 
 ```bash
-conda run -n coreai backends/apple/coreai/run_all_tests.sh
+python -m pytest backends/apple/coreai
 ```
 
-Extra args are forwarded to `unittest`, e.g. `... run_all_tests.sh -v` or
-`... run_all_tests.sh -k sidecar`.
-
-**Use this script (unittest), not `pytest` directly.** pytest's default
-discovery puts `backends/apple/` on `sys.path`, so `import coreai` resolves to
-this backend directory and shadows the real Apple `coreai` SDK (`coreai_torch`
-then fails importing `coreai.authoring`). unittest imports via the full
-`executorch.backends.apple.coreai.*` path and avoids the shadowing.
+Standard pytest options apply, e.g. `-v` or `-k sidecar`.
 
 The real-toolchain AOT test (`CoreAIAOTCompileTest`) is gated on
 `xcrun coreai-build`; it runs on macOS with the Metal Toolchain and skips