Add llama jobs on Arm64 and reduce llama jobs on MacOS

Author: mergennachin

.github/workflows/pull.yml

@@ -136,6 +136,7 @@ jobs:
         PYTHON_EXECUTABLE=python bash .ci/scripts/test_model.sh "${MODEL_NAME}" "${BUILD_TOOL}" "${BACKEND}"
 
   test-llama-runner-linux:
+    # Test Both linux x86 and linux aarch64
     name: test-llama-runner-linux
     uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
     permissions:
@@ -145,15 +146,37 @@ jobs:
       matrix:
         dtype: [fp32]
         mode: [portable, xnnpack+custom, xnnpack+custom+qe,xnnpack+custom+quantize_kv,xnnpack+quantize_kv]
+        runner: [linux.2xlarge, linux.arm64.2xlarge]
+        docker-image: [executorch-ubuntu-22.04-clang12, executorch-ubuntu-22.04-gcc11-aarch64]
         include:
           - dtype: bf16
             mode: portable
+            runner: linux.2xlarge
+            docker-image: executorch-ubuntu-22.04-clang12
           - dtype: bf16
             mode: custom
+            runner: linux.2xlarge
+            docker-image: executorch-ubuntu-22.04-clang12
+          - dtype: bf16
+            mode: portable
+            runner: linux.arm64.2xlarge
+            docker-image: executorch-ubuntu-22.04-gcc11-aarch64
+          - dtype: bf16
+            mode: custom
+            runner: linux.arm64.2xlarge
+            docker-image: executorch-ubuntu-22.04-gcc11-aarch64
+        # Excluding specific runner + docker image combinations that don't make sense:
+        #   - Excluding the ARM64 gcc image on the x86 runner (linux.2xlarge)
+        #   - Excluding the x86 clang image on the ARM64 runner (linux.arm64.2xlarge)
+        exclude:
+          - runner: linux.2xlarge
+            docker-image: executorch-ubuntu-22.04-gcc11-aarch64
+          - runner: linux.arm64.2xlarge
+            docker-image: executorch-ubuntu-22.04-clang12
       fail-fast: false
     with:
-      runner: linux.2xlarge
-      docker-image: executorch-ubuntu-22.04-clang12
+      runner: ${{ matrix.runner }}
+      docker-image: ${{ matrix.docker-image }}
       submodules: 'true'
       ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
       timeout: 900

.github/workflows/trunk.yml

@@ -289,12 +289,7 @@ jobs:
     strategy:
       matrix:
         dtype: [fp32]
-        mode: [portable, xnnpack+kv+custom, mps, coreml, xnnpack+custom+quantize_kv]
-        include:
-          - dtype: bf16
-            mode: portable
-          - dtype: bf16
-            mode: custom
+        mode: [mps, coreml, xnnpack+custom+quantize_kv]
       fail-fast: false
     with:
       runner: macos-m1-stable