diff --git a/.github/workflows/docker.yml b/.github/workflows/docker.yml deleted file mode 100644 index bf94b2024..000000000 --- a/.github/workflows/docker.yml +++ /dev/null @@ -1,116 +0,0 @@ -# This workflow uses actions that are not certified by GitHub. -# They are provided by a third-party and are governed by -# separate terms of service, privacy policy, and support -# documentation. - -# GitHub recommends pinning actions to a commit SHA. -# To get a newer version, you will need to update the SHA. -# You can also reference a tag or branch, but the action may change without warning. - -name: Publish Docker image - -on: - #pull_request: - push: - branches: - - master - paths: ['.github/workflows/docker.yml', '.devops/*.Dockerfile', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.swift', '**/*.m', '**/*.metal'] - -concurrency: - group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} - cancel-in-progress: true - -jobs: - push_to_registry: - name: Push Docker image to Docker Hub - #if: github.event.pull_request.draft == false - - runs-on: ubuntu-latest - env: - COMMIT_SHA: ${{ github.sha }} - strategy: - matrix: - config: - - { tag: "light", dockerfile: ".devops/llama-cli.Dockerfile", platforms: "linux/amd64,linux/arm64" } - - { tag: "server", dockerfile: ".devops/llama-server.Dockerfile", platforms: "linux/amd64,linux/arm64" } - - { tag: "full", dockerfile: ".devops/full.Dockerfile", platforms: "linux/amd64,linux/arm64" } - - { tag: "light-cuda", dockerfile: ".devops/llama-cli-cuda.Dockerfile", platforms: "linux/amd64" } - - { tag: "server-cuda", dockerfile: ".devops/llama-server-cuda.Dockerfile", platforms: "linux/amd64" } - - { tag: "full-cuda", dockerfile: ".devops/full-cuda.Dockerfile", platforms: "linux/amd64" } - - { tag: "light-rocm", dockerfile: ".devops/llama-cli-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" } - - { tag: "server-rocm", dockerfile: ".devops/llama-server-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" } - # Note: the full-rocm image is failing due to a "no space left on device" error. It is disabled for now to allow the workflow to complete. - #- { tag: "full-rocm", dockerfile: ".devops/full-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" } - - { tag: "light-intel", dockerfile: ".devops/llama-cli-intel.Dockerfile", platforms: "linux/amd64" } - - { tag: "server-intel", dockerfile: ".devops/llama-server-intel.Dockerfile", platforms: "linux/amd64" } - steps: - - name: Check out the repo - uses: actions/checkout@v4 - - - name: Set up QEMU - uses: docker/setup-qemu-action@v2 - - - name: Set up Docker Buildx - uses: docker/setup-buildx-action@v2 - - - name: Log in to Docker Hub - uses: docker/login-action@v2 - with: - registry: ghcr.io - username: ${{ github.repository_owner }} - password: ${{ secrets.GITHUB_TOKEN }} - - # https://github.com/jlumbroso/free-disk-space/tree/54081f138730dfa15788a46383842cd2f914a1be#example - - name: Free Disk Space (Ubuntu) - uses: jlumbroso/free-disk-space@main - with: - # this might remove tools that are actually needed, - # if set to "true" but frees about 6 GB - tool-cache: false - - # all of these default to true, but feel free to set to - # "false" if necessary for your workflow - android: true - dotnet: true - haskell: true - large-packages: true - docker-images: true - swap-storage: true - - - name: Determine tag name - id: tag - shell: bash - run: | - BUILD_NUMBER="$(git rev-list --count HEAD)" - SHORT_HASH="$(git rev-parse --short=7 HEAD)" - if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then - echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT - else - SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-') - echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT - fi - - - name: Downcase github.repository_owner - run: | - echo "repository_owner_lowercase=${GITHUB_REPOSITORY_OWNER@L}" >> $GITHUB_ENV - env: - GITHUB_REPOSITORY_OWNER: '${{ github.repository_owner }}' - - - name: Build and push Docker image (versioned) - if: github.event_name == 'push' - uses: docker/build-push-action@v4 - with: - context: . - push: true - platforms: ${{ matrix.config.platforms }} - tags: "ghcr.io/${{ env.repository_owner_lowercase }}/llama.cpp:${{ matrix.config.tag }}-${{ env.COMMIT_SHA }}" - file: ${{ matrix.config.dockerfile }} - - - name: Build and push Docker image (tagged) - uses: docker/build-push-action@v4 - with: - context: . - push: ${{ github.event_name == 'push' }} - platforms: ${{ matrix.config.platforms }} - tags: "ghcr.io/${{ env.repository_owner_lowercase }}/llama.cpp:${{ matrix.config.tag }},ghcr.io/${{ env.repository_owner_lowercase }}/llama.cpp:${{ matrix.config.tag }}-${{ steps.tag.outputs.name }}" - file: ${{ matrix.config.dockerfile }} diff --git a/.github/workflows/server.yml b/.github/workflows/server.yml deleted file mode 100644 index 99feb28f2..000000000 --- a/.github/workflows/server.yml +++ /dev/null @@ -1,183 +0,0 @@ -# Server build and tests -name: Server - -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.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'examples/server/**.*'] - pull_request: - types: [opened, synchronize, reopened] - paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'examples/server/**.*'] - -concurrency: - group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }} - cancel-in-progress: true - -jobs: - server: - runs-on: ubuntu-latest - - strategy: - matrix: - sanitizer: [ADDRESS, UNDEFINED] # THREAD is broken - build_type: [RelWithDebInfo] - include: - - build_type: Release - sanitizer: "" - fail-fast: false # While -DLLAMA_SANITIZE_THREAD=ON is broken - - steps: - - name: Dependencies - id: depends - run: | - sudo apt-get update - sudo apt-get -y install \ - build-essential \ - xxd \ - git \ - cmake \ - curl \ - wget \ - language-pack-en \ - libcurl4-openssl-dev - - - name: Clone - id: checkout - uses: actions/checkout@v4 - with: - fetch-depth: 0 - ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }} - - - name: Python setup - id: setup_python - uses: actions/setup-python@v5 - with: - python-version: '3.11' - - - name: Tests dependencies - id: test_dependencies - run: | - pip install -r examples/server/tests/requirements.txt - - - name: Verify server deps - id: verify_server_deps - run: | - git config --global --add safe.directory $(realpath .) - cd examples/server - git ls-files --others --modified - git status - ./deps.sh - git status - not_ignored_files="$(git ls-files --others --modified)" - echo "Modified files: ${not_ignored_files}" - if [ -n "${not_ignored_files}" ]; then - echo "Repository is dirty or server deps are not built as expected" - echo "${not_ignored_files}" - exit 1 - fi - - - name: Build (no OpenMP) - id: cmake_build_no_openmp - if: ${{ matrix.sanitizer == 'THREAD' }} - run: | - cmake -B build \ - -DGGML_NATIVE=OFF \ - -DLLAMA_BUILD_SERVER=ON \ - -DLLAMA_CURL=ON \ - -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \ - -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ - -DGGML_OPENMP=OFF ; - cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target llama-server - - - name: Build - id: cmake_build - if: ${{ matrix.sanitizer != 'THREAD' }} - run: | - cmake -B build \ - -DGGML_NATIVE=OFF \ - -DLLAMA_BUILD_SERVER=ON \ - -DLLAMA_CURL=ON \ - -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \ - -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON ; - cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target llama-server - - - name: Tests - id: server_integration_tests - run: | - cd examples/server/tests - PORT=8888 ./tests.sh - - - name: Slow tests - id: server_integration_tests_slow - if: ${{ (github.event.schedule || github.event.inputs.slow_tests == 'true') && matrix.build_type == 'Release' }} - run: | - cd examples/server/tests - PORT=8888 ./tests.sh --stop --no-skipped --no-capture --tags slow - - - server-windows: - runs-on: windows-2019 - - steps: - - name: Clone - id: checkout - uses: actions/checkout@v4 - with: - fetch-depth: 0 - ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }} - - - name: libCURL - id: get_libcurl - env: - CURL_VERSION: 8.6.0_6 - run: | - curl.exe -o $env:RUNNER_TEMP/curl.zip -L "https://curl.se/windows/dl-${env:CURL_VERSION}/curl-${env:CURL_VERSION}-win64-mingw.zip" - mkdir $env:RUNNER_TEMP/libcurl - tar.exe -xvf $env:RUNNER_TEMP/curl.zip --strip-components=1 -C $env:RUNNER_TEMP/libcurl - - - name: Build - id: cmake_build - run: | - cmake -B build -DLLAMA_CURL=ON -DCURL_LIBRARY="$env:RUNNER_TEMP/libcurl/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:RUNNER_TEMP/libcurl/include" - cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS} --target llama-server - - - name: Python setup - id: setup_python - uses: actions/setup-python@v5 - with: - python-version: '3.11' - - - name: Tests dependencies - id: test_dependencies - run: | - pip install -r examples/server/tests/requirements.txt - - - name: Copy Libcurl - id: prepare_libcurl - run: | - cp $env:RUNNER_TEMP/libcurl/bin/libcurl-x64.dll ./build/bin/Release/libcurl-x64.dll - - - name: Tests - id: server_integration_tests - if: ${{ !matrix.disabled_on_pr || !github.event.pull_request }} - run: | - cd examples/server/tests - behave.exe --summary --stop --no-capture --exclude 'issues|wrong_usages|passkey' --tags llama.cpp - - - name: Slow tests - id: server_integration_tests_slow - if: ${{ (github.event.schedule || github.event.inputs.slow_tests == 'true') && matrix.build_type == 'Release' }} - run: | - cd examples/server/tests - behave.exe --stop --no-skipped --no-capture --tags slow