Release #3
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: Release | |
| on: | |
| workflow_dispatch: # allows manual triggering | |
| inputs: | |
| create_release: | |
| description: 'Create new release' | |
| required: true | |
| type: boolean | |
| push: | |
| branches: | |
| - master | |
| paths: ['.github/workflows/release.yml', '**/CMakeLists.txt', '**/.cmake', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.cuh', '**/*.m', '**/*.comp'] | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }} | |
| cancel-in-progress: true | |
| env: | |
| BRANCH_NAME: ${{ github.head_ref || github.ref_name }} | |
| CMAKE_ARGS: "-DLLAMA_BUILD_EXAMPLES=OFF -DLLAMA_BUILD_TESTS=OFF -DLLAMA_BUILD_TOOLS=ON -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON" | |
| jobs: | |
| # ubuntu-22-vulkan: | |
| # if: false | |
| # runs-on: ubuntu-22.04 | |
| # steps: | |
| # - name: Clone | |
| # id: checkout | |
| # uses: actions/checkout@v4 | |
| # with: | |
| # fetch-depth: 0 | |
| # - name: ccache | |
| # uses: hendrikmuhs/ccache-action@v1.2.18 | |
| # with: | |
| # key: ubuntu-22-cmake-vulkan | |
| # evict-old-files: 1d | |
| # - name: Dependencies | |
| # id: depends | |
| # run: | | |
| # wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | sudo apt-key add - | |
| # sudo wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list | |
| # sudo apt-get update -y | |
| # sudo apt-get install -y build-essential mesa-vulkan-drivers vulkan-sdk libcurl4-openssl-dev | |
| # - name: Build | |
| # id: cmake_build | |
| # run: | | |
| # cmake -B build \ | |
| # -DGGML_VULKAN=ON \ | |
| # -DGGML_MAX_CONTEXTS=2048 \ | |
| # ${{ env.CMAKE_ARGS }} | |
| # cmake --build build --config Release -j $(nproc) | |
| # - name: Determine tag name | |
| # id: tag | |
| # uses: ./.github/actions/get-tag-name | |
| # - name: Pack artifacts | |
| # id: pack_artifacts | |
| # run: | | |
| # cp LICENSE ./build/bin/ | |
| # zip -r llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip ./build/bin/* | |
| # - name: Upload artifacts | |
| # uses: actions/upload-artifact@v4 | |
| # with: | |
| # path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.zip | |
| # name: llama-bin-ubuntu-vulkan-x64.zip | |
| windows-cuda: | |
| runs-on: windows-2022 | |
| strategy: | |
| matrix: | |
| cuda: ['12.6'] # | |
| instr: ['avx2' ] # 'avx512', 'avx512bf16' | |
| steps: | |
| - name: Clone | |
| id: checkout | |
| uses: actions/checkout@v4 | |
| - name: Install ccache | |
| uses: hendrikmuhs/ccache-action@v1.2.18 | |
| with: | |
| key: windows-cuda-${{ matrix.cuda }}-${{ matrix.instr }} | |
| variant: ccache | |
| evict-old-files: 1d | |
| - name: Install CUDA Toolkit | |
| uses: ./.github/actions/windows-setup-cuda | |
| with: | |
| cuda_version: ${{ matrix.cuda }} | |
| - name: Install Ninja | |
| id: install_ninja | |
| run: | | |
| choco install ninja | |
| - name: Build | |
| id: cmake_build | |
| shell: cmd | |
| run: | | |
| call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvarsall.bat" x64 | |
| cmake -S . -B build -G "Ninja Multi-Config" -DLLAMA_BUILD_SERVER=ON ^ | |
| -DGGML_CUDA_FA_ALL_QUANTS=ON -DGGML_CUDA=ON ^ | |
| -DGGML_OPENMP=ON -DGGML_AVX2=ON ^ | |
| -DGGML_AVX2=${{ (matrix.instr == 'avx2' || matrix.instr == 'avx512' || matrix.instr == 'avx512bf16') && 'ON' || 'OFF' }} ^ | |
| -DGGML_NATIVE=OFF -DLLAMA_CURL=OFF ^ | |
| -DGGML_SCHED_MAX_COPIES=1 ^ | |
| -DGGML_CUDA_IQK_FORCE_BF16=1 ^ | |
| -DGGML_MAX_CONTEXTS=4096 | |
| set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1 | |
| cmake --build build --config Release -j %NINJA_JOBS% | |
| - name: Pack artifacts | |
| id: pack_artifacts | |
| run: | | |
| 7z a llama-bin-win-cuda-${{ matrix.cuda }}.zip .\build\bin\Release\* | |
| - name: Upload artifacts | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| path: llama-bin-win-cuda-${{ matrix.cuda }}.zip | |
| name: llama-bin-win-cuda-${{ matrix.cuda }}.zip | |
| release: | |
| if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }} | |
| # Fine-grant permission | |
| # https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token | |
| permissions: | |
| contents: write # for creating release | |
| runs-on: ubuntu-latest | |
| needs: | |
| #- windows | |
| - windows-cuda | |
| #- windows-hip | |
| #- ubuntu-22-cpu | |
| #- ubuntu-22-vulkan | |
| steps: | |
| - name: Clone | |
| id: checkout | |
| uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 0 | |
| - name: Determine tag name | |
| id: tag | |
| uses: ./.github/actions/get-tag-name | |
| - name: Download artifacts | |
| id: download-artifact | |
| uses: actions/download-artifact@v4 | |
| with: | |
| path: ./artifact | |
| merge-multiple: true | |
| - name: Move artifacts | |
| id: move_artifacts | |
| # artifact/cudart-llama-bin-win-*.zip | |
| run: | | |
| mkdir -p release | |
| echo "Adding cuda backend files to existing zips..." | |
| for arch in x64; do | |
| cpu_zip="artifact/llama-bin-win-${arch}.zip" | |
| temp_dir=$(mktemp -d) | |
| echo "Extracting CPU backend for $arch..." | |
| unzip "$cpu_zip" -d "$temp_dir" | |
| echo "Adding CPU files to $arch zips..." | |
| for target_zip in artifact/llama-bin-win-*-${arch}.zip; do | |
| if [[ "$target_zip" == "$cpu_zip" ]]; then | |
| continue | |
| fi | |
| echo "Adding CPU backend to $(basename "$target_zip")" | |
| realpath_target_zip=$(realpath "$target_zip") | |
| (cd "$temp_dir" && zip -r "$realpath_target_zip" .) | |
| done | |
| rm -rf "$temp_dir" | |
| done | |
| echo "Renaming and moving zips to release..." | |
| for zip_file in artifact/llama-bin-win-*.zip; do | |
| base_name=$(basename "$zip_file" .zip) | |
| zip_name="ik_llama-${{ steps.tag.outputs.name }}-${base_name#llama-}.zip" | |
| echo "Moving $zip_file to release/$zip_name" | |
| mv "$zip_file" "release/$zip_name" | |
| done | |
| echo "Moving any remaining artifacts..." | |
| mv -v artifact/*.zip release/ || true | |
| - name: Create release | |
| id: create_release | |
| uses: Thireus/action-create-release@v1 | |
| env: | |
| GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| with: | |
| tag_name: ${{ steps.tag.outputs.name }} | |
| - name: Upload release | |
| id: upload_release | |
| uses: actions/github-script@v3 | |
| with: | |
| github-token: ${{secrets.GITHUB_TOKEN}} | |
| script: | | |
| const path = require('path'); | |
| const fs = require('fs'); | |
| const release_id = '${{ steps.create_release.outputs.id }}'; | |
| for (let file of await fs.readdirSync('./release')) { | |
| if (path.extname(file) === '.zip') { | |
| console.log('uploadReleaseAsset', file); | |
| await github.repos.uploadReleaseAsset({ | |
| owner: context.repo.owner, | |
| repo: context.repo.repo, | |
| release_id: release_id, | |
| name: file, | |
| data: await fs.readFileSync(`./release/${file}`) | |
| }); | |
| } | |
| } |