enable llama test for qnn

Author: shewu-quic

.github/workflows/pull.yml

@@ -372,3 +372,38 @@ jobs:
 
         # Run pytest with coverage
         pytest -c /dev/null -v -n auto --cov=./ --cov-report=xml backends/arm/test
+
+
+  test-llama-runner-qnn-linux:
+    name: test-llama-runner-qnn-linux
+    uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
+    strategy:
+      matrix:
+        dtype: [fp32]
+        build-tool: [cmake]
+        mode: [qnn]
+      fail-fast: false
+    with:
+      runner: linux.2xlarge
+      docker-image: executorch-ubuntu-22.04-clang12-android
+      submodules: 'true'
+      ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
+      timeout: 900
+      script: |
+        # The generic Linux job chooses to use base env, not the one setup by the image
+        CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
+        conda activate "${CONDA_ENV}"
+
+        DTYPE=${{ matrix.dtype }}
+        BUILD_TOOL=${{ matrix.build-tool }}
+        MODE=${{ matrix.mode }}
+
+        PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
+        PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh
+
+        # Setup executorch
+        PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh buck2
+        # Install requirements for export_llama
+        PYTHON_EXECUTABLE=python bash examples/models/llama2/install_requirements.sh
+        # Test llama2
+        PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh stories110M "${BUILD_TOOL}" "${DTYPE}" "${MODE}"