Update on "[executorch][PR] add cuda backend to backend test infra"

Integrate cuda backend into backend test infra; skipped the unsupported test for now

Differential Revision: [D93019490](https://our.internmc.facebook.com/intern/diff/D93019490/)

[ghstack-poisoned]

Author: Gasoonjia

.ci/scripts/test_backend.sh

@@ -63,6 +63,16 @@ if [[ "$FLOW" == *cuda* ]]; then
     echo "Installing newer libstdc++ for CUDA backend..."
     conda install -y -c conda-forge 'libstdcxx-ng>=12'
     export LD_LIBRARY_PATH="${CONDA_PREFIX}/lib:${LD_LIBRARY_PATH:-}"
+
+    # CUDA backend uses the generic PyTorch test-infra Docker image (not the
+    # custom executorch image), so PyTorch is NOT pre-installed from a pinned
+    # commit.  Install executorch with nightly PyTorch (which auto-detects
+    # CUDA via nvcc) and then build the runner manually.
+    echo "Installing ExecuTorch with nightly PyTorch (CUDA-enabled)..."
+    ./install_executorch.sh --editable
+    CMAKE_ARGS="$EXTRA_BUILD_ARGS" source .ci/scripts/utils.sh
+    build_executorch_runner cmake Release
+    CUDA_SETUP_DONE=1
 fi
 
 if [[ "$FLOW" == *arm* ]]; then
@@ -87,12 +97,14 @@ if [[ "$FLOW" == *arm* ]]; then
     fi
 fi
 
-if [[ $IS_MACOS -eq 1 ]]; then
-    SETUP_SCRIPT=.ci/scripts/setup-macos.sh
-else
-    SETUP_SCRIPT=.ci/scripts/setup-linux.sh
+if [[ "${CUDA_SETUP_DONE:-0}" != "1" ]]; then
+    if [[ $IS_MACOS -eq 1 ]]; then
+        SETUP_SCRIPT=.ci/scripts/setup-macos.sh
+    else
+        SETUP_SCRIPT=.ci/scripts/setup-linux.sh
+    fi
+    CMAKE_ARGS="$EXTRA_BUILD_ARGS" ${CONDA_RUN_CMD} $SETUP_SCRIPT --build-tool cmake --build-mode Release --editable true
 fi
-CMAKE_ARGS="$EXTRA_BUILD_ARGS" ${CONDA_RUN_CMD} $SETUP_SCRIPT --build-tool cmake --build-mode Release --editable true
 
 GOLDEN_DIR="${ARTIFACT_DIR}/golden-artifacts"
 export GOLDEN_ARTIFACTS_DIR="${GOLDEN_DIR}"

.github/workflows/_test_backend.yml

@@ -36,6 +36,26 @@ on:
         required: false
         type: string
         default: linux.4xlarge.memory
+      docker-image:
+        description: 'Docker image for Linux jobs'
+        required: false
+        type: string
+        default: ci-image:executorch-ubuntu-22.04-clang12
+      use-custom-docker-registry:
+        description: 'Whether to use a custom Docker registry (set false for CUDA to use default PyTorch test-infra images)'
+        required: false
+        type: boolean
+        default: true
+      gpu-arch-type:
+        description: 'GPU architecture type (e.g. cuda)'
+        required: false
+        type: string
+        default: ''
+      gpu-arch-version:
+        description: 'GPU architecture version (e.g. 12.6)'
+        required: false
+        type: string
+        default: ''
 
 jobs:
   test-backend-linux:
@@ -50,7 +70,10 @@ jobs:
     with:
       ref: ${{ inputs.ref }}
       runner: ${{ inputs.runner-linux }}
-      docker-image: ci-image:executorch-ubuntu-22.04-clang12
+      docker-image: ${{ inputs.docker-image }}
+      use-custom-docker-registry: ${{ inputs.use-custom-docker-registry }}
+      gpu-arch-type: ${{ inputs.gpu-arch-type }}
+      gpu-arch-version: ${{ inputs.gpu-arch-version }}
       submodules: recursive
       timeout: ${{ inputs.timeout }}
       upload-artifact: test-report-${{ matrix.flow }}-${{ matrix.suite }}

.github/workflows/test-backend-cuda.yml

@@ -28,3 +28,6 @@ jobs:
       timeout: 120
       run-linux: true
       runner-linux: linux.g5.4xlarge.nvidia.gpu
+      use-custom-docker-registry: false
+      gpu-arch-type: cuda
+      gpu-arch-version: '12.6'