# pip install -r requirements.txt
# export ${{ matrix.extra_args }}
# pytest -v -x -m "not slow"
+
+ server-kleidiai:
+ runs-on: ah-ubuntu_22_04-c8g_8x
+
+ name: server-kleidiai (${{ matrix.wf_name }})
+ strategy:
+ matrix:
+ include:
+ - build_type: Release
+ extra_build_flags: "-DGGML_CPU_KLEIDIAI=ON"
+ extra_args: ""
+ wf_name: "CPUx1, kleidiai"
+ fail-fast: false
+
+ steps:
+ - name: Clone
+ id: checkout
+ uses: actions/checkout@v6
+ with:
+ fetch-depth: 0
+ ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
+
+ - name: Build
+ id: cmake_build
+ run: |
+ cmake -B build -DGGML_SCHED_NO_REALLOC=ON ${{ matrix.extra_build_flags }}
+ cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target llama-server
+
+ - name: Tests
+ id: server_integration_tests
+ if: ${{ (!matrix.disabled_on_pr || !github.event.pull_request) }}
+ run: |
+ cd tools/server/tests
+ python3 -m venv venv
+ source venv/bin/activate
+ pip install -r requirements.txt
+ export ${{ matrix.extra_args }}
+ pytest -v -x -m "not slow"