Server (self-hosted) #7
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Server (self-hosted) | |
| on: | |
| workflow_dispatch: # allows manual triggering | |
| inputs: | |
| sha: | |
| description: 'Commit SHA1 to build' | |
| required: false | |
| type: string | |
| slow_tests: | |
| description: 'Run slow tests' | |
| required: true | |
| type: boolean | |
| push: | |
| branches: | |
| - master | |
| paths: [ | |
| '.github/workflows/server-self-hosted.yml', | |
| '**/CMakeLists.txt', | |
| '**/Makefile', | |
| '**/*.h', | |
| '**/*.hpp', | |
| '**/*.c', | |
| '**/*.cpp', | |
| '**/*.cu', | |
| '**/*.swift', | |
| '**/*.m', | |
| 'tools/server/**.*' | |
| ] | |
| env: | |
| LLAMA_LOG_COLORS: 1 | |
| LLAMA_LOG_PREFIX: 1 | |
| LLAMA_LOG_TIMESTAMPS: 1 | |
| LLAMA_LOG_VERBOSITY: 10 | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }} | |
| cancel-in-progress: true | |
| jobs: | |
| server-metal: | |
| runs-on: [self-hosted, llama-server, macOS, ARM64] | |
| name: server-metal (${{ matrix.wf_name }}) | |
| strategy: | |
| matrix: | |
| build_type: [Release] | |
| wf_name: ["GPUx1"] | |
| include: | |
| - build_type: Release | |
| extra_args: "LLAMA_ARG_BACKEND_SAMPLING=1" | |
| wf_name: "GPUx1, backend-sampling" | |
| - build_type: Release | |
| extra_args: "GGML_METAL_DEVICES=2" | |
| wf_name: "GPUx2" | |
| - build_type: Release | |
| extra_args: "GGML_METAL_DEVICES=2 LLAMA_ARG_BACKEND_SAMPLING=1" | |
| wf_name: "GPUx2, backend-sampling" | |
| 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: Setup Node.js | |
| uses: actions/setup-node@v6 | |
| with: | |
| node-version: "24" | |
| cache: "npm" | |
| cache-dependency-path: "tools/ui/package-lock.json" | |
| - name: Build | |
| id: cmake_build | |
| run: | | |
| cmake -B build -DGGML_SCHED_NO_REALLOC=ON | |
| cmake --build build --config ${{ matrix.build_type }} -j $(sysctl -n hw.logicalcpu) --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 ${{ matrix.extra_args }} | |
| pytest -v -x -m "not slow" | |
| server-cuda: | |
| runs-on: [self-hosted, llama-server, Linux, NVIDIA] | |
| name: server-cuda (${{ matrix.wf_name }}) | |
| strategy: | |
| matrix: | |
| build_type: [Release] | |
| wf_name: ["GPUx1"] | |
| include: | |
| - build_type: Release | |
| extra_args: "LLAMA_ARG_BACKEND_SAMPLING=1" | |
| wf_name: "GPUx1, backend-sampling" | |
| 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 | |
| cmake --build build --config ${{ matrix.build_type }} -j $(sysctl -n hw.logicalcpu) --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 ${{ matrix.extra_args }} | |
| pytest -v -x -m "not slow" | |
| server-kleidiai: | |
| runs-on: ah-ubuntu_22_04-c8g_8x | |
| name: server-kleidiai (${{ 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: Dependencies | |
| id: depends | |
| run: | | |
| set -euxo pipefail | |
| sudo apt-get update | |
| sudo DEBIAN_FRONTEND=noninteractive NEEDRESTART_MODE=a \ | |
| apt-get install -y \ | |
| build-essential \ | |
| libssl-dev \ | |
| python3-venv \ | |
| gpg \ | |
| wget \ | |
| time \ | |
| git-lfs | |
| git lfs install | |
| # install the latest cmake | |
| sudo install -d /usr/share/keyrings | |
| wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc \ | |
| | gpg --dearmor \ | |
| | sudo tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null | |
| echo 'deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ jammy main' \ | |
| | sudo tee /etc/apt/sources.list.d/kitware.list | |
| sudo apt-get update | |
| sudo apt-get install -y cmake | |
| - 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" |