move to trunk

Author: cccclai

.github/workflows/pull.yml

@@ -591,42 +591,6 @@ jobs:
         # Test static llama weight sharing and accuracy
         PYTHON_EXECUTABLE=python bash .ci/scripts/test_qnn_static_llama.sh
 
-  test-static-llama-qnn-eval-linux:
-    name: test-static-llama-qnn-eval-linux
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
-    permissions:
-      id-token: write
-      contents: read
-    strategy:
-      fail-fast: false
-      matrix:
-        config:
-          - name: "baseline"
-            flags: ""
-            threshold: 62.0
-    with:
-      runner: linux.2xlarge
-      docker-image: ci-image:executorch-ubuntu-22.04-qnn-sdk
-      submodules: 'recursive'
-      ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
-      timeout: 180
-      script: |
-        # The generic Linux job chooses to use base env, not the one setup by the image
-        CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
-        conda activate "${CONDA_ENV}"
-        BUILD_TOOL="cmake"
-        PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
-        PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh
-        # Setup executorch
-        PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
-        # Setup install_requirements for llama
-        PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
-
-        echo ">>> Running config: ${{ matrix.config.name }}"
-        PYTHON_EXECUTABLE=python bash .ci/scripts/test_qnn_static_llama_eval.sh \
-          --flags "${{ matrix.config.flags }}" \
-          --threshold "${{ matrix.config.threshold }}"
-
   test-qnn-models-linux:
     name: test-qnn-models-linux
     uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main

.github/workflows/trunk.yml

@@ -973,6 +973,42 @@ jobs:
         # Test llama2
         PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh -model stories110M -build_tool "${BUILD_TOOL}" -mode "${MODE}" -dtype "${DTYPE}" -pt2e_quantize "${PT2E_QUANTIZE}"
 
+  test-static-llama-qnn-eval-linux:
+    name: test-static-llama-qnn-eval-linux
+    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    permissions:
+      id-token: write
+      contents: read
+    strategy:
+      fail-fast: false
+      matrix:
+        config:
+          - name: "baseline"
+            flags: ""
+            threshold: 62.0
+    with:
+      runner: linux.2xlarge
+      docker-image: ci-image:executorch-ubuntu-22.04-qnn-sdk
+      submodules: 'recursive'
+      ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
+      timeout: 180
+      script: |
+        # The generic Linux job chooses to use base env, not the one setup by the image
+        CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
+        conda activate "${CONDA_ENV}"
+        BUILD_TOOL="cmake"
+        PYTHON_EXECUTABLE=python bash .ci/scripts/setup-qnn-deps.sh
+        PYTHON_EXECUTABLE=python bash .ci/scripts/build-qnn-sdk.sh
+        # Setup executorch
+        PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool "${BUILD_TOOL}"
+        # Setup install_requirements for llama
+        PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
+
+        echo ">>> Running config: ${{ matrix.config.name }}"
+        PYTHON_EXECUTABLE=python bash .ci/scripts/test_qnn_static_llama_eval.sh \
+          --flags "${{ matrix.config.flags }}" \
+          --threshold "${{ matrix.config.threshold }}"
+
   unittest-release:
     uses: ./.github/workflows/_unittest.yml
     permissions: