ollama/.github/workflows/test.yaml

name: test

concurrency:
  # For PRs, later CI runs preempt previous ones. e.g. a force push on a PR
  # cancels running CI jobs and starts all new ones.
  #
  # For non-PR pushes, concurrency.group needs to be unique for every distinct
  # CI run we want to have happen. Use run_id, which in practice means all
  # non-PR CI runs will be allowed to run without preempting each other.
  group: ${{ github.workflow }}-$${{ github.pull_request.number || github.run_id }}
  cancel-in-progress: true

on:
  pull_request:
    paths:
      - '**/*'
      - '!docs/**'
      - '!README.md'

jobs:
  changes:
    runs-on: ubuntu-latest
    outputs:
      changed: ${{ steps.changes.outputs.changed }}
      vendorsha: ${{ steps.changes.outputs.vendorsha }}
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
      - id: changes
        run: |
          changed() {
            local BASE=${{ github.event.pull_request.base.sha }}
            local HEAD=${{ github.event.pull_request.head.sha }}
            local MERGE_BASE=$(git merge-base $BASE $HEAD)
            git diff-tree -r --no-commit-id --name-only "$MERGE_BASE" "$HEAD" \
              | xargs python3 -c "import sys; from pathlib import Path; print(any(Path(x).match(glob) for x in sys.argv[1:] for glob in '$*'.split(' ')))"
          }

          echo changed=$(changed 'llama/server/**/*' 'LLAMA_CPP_VERSION' '.github/**/*') | tee -a $GITHUB_OUTPUT
          echo vendorsha=$(cat LLAMA_CPP_VERSION) | tee -a $GITHUB_OUTPUT

  linux:
    needs: [changes]
    if: needs.changes.outputs.changed == 'True'
    strategy:
      matrix:
        include:
          - preset: CPU
          - preset: CUDA
            container: nvidia/cuda:13.0.0-devel-ubuntu22.04
            flags: '-DCMAKE_CUDA_ARCHITECTURES=87'
          - preset: ROCm
            container: rocm/dev-ubuntu-22.04:7.2.1
            extra-packages: rocm-libs
            flags: '-DAMDGPU_TARGETS=gfx1010 -DCMAKE_PREFIX_PATH=/opt/rocm'
          - preset: Vulkan
            container: ubuntu:22.04
            extra-packages: >
              mesa-vulkan-drivers vulkan-tools
              libvulkan1 libvulkan-dev
              vulkan-sdk cmake ccache g++ make
          - preset: 'MLX CUDA 13'
            container: nvidia/cuda:13.0.0-devel-ubuntu22.04
            extra-packages: libcudnn9-dev-cuda-13 libopenblas-dev liblapack-dev liblapacke-dev git curl
            flags: '-DCMAKE_CUDA_ARCHITECTURES=87 -DBLAS_INCLUDE_DIRS=/usr/include/x86_64-linux-gnu -DLAPACK_INCLUDE_DIRS=/usr/include/x86_64-linux-gnu'
            install-go: true
    runs-on: linux
    container: ${{ matrix.container }}
    steps:
      - uses: actions/checkout@v4
      - run: |
          [ -n "${{ matrix.container }}" ] || sudo=sudo
          $sudo apt-get update
          # Add LunarG Vulkan SDK apt repo for Ubuntu 22.04
          if [ "${{ matrix.preset }}" = "Vulkan" ]; then
            $sudo apt-get install -y --no-install-recommends wget gnupg ca-certificates software-properties-common
            wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | $sudo gpg --dearmor -o /usr/share/keyrings/lunarg-archive-keyring.gpg
            # Use signed-by to bind the repo to the installed keyring to avoid NO_PUBKEY
            echo "deb [signed-by=/usr/share/keyrings/lunarg-archive-keyring.gpg]  https://packages.lunarg.com/vulkan/1.4.313 jammy main" | $sudo tee /etc/apt/sources.list.d/lunarg-vulkan-1.4.313-jammy.list > /dev/null
            $sudo apt-get update
          fi
          $sudo apt-get install -y cmake ccache curl ${{ matrix.extra-packages }}
          # llama-server requires CMake 3.24+, while Ubuntu 22.04 ships 3.22.
          curl -fsSL https://github.com/Kitware/CMake/releases/download/v3.31.2/cmake-3.31.2-linux-$(uname -m).tar.gz | $sudo tar xz -C /usr/local --strip-components 1
          # Export VULKAN_SDK if provided by LunarG package (defensive)
          if [ -d "/usr/lib/x86_64-linux-gnu/vulkan" ] && [ "${{ matrix.preset }}" = "Vulkan" ]; then
            echo "VULKAN_SDK=/usr" >> $GITHUB_ENV
          fi
        env:
          DEBIAN_FRONTEND: noninteractive
      - if: matrix.install-go
        name: Install Go
        run: |
          GO_VERSION=$(awk '/^go / { print $2 }' go.mod)
          curl -fsSL "https://golang.org/dl/go${GO_VERSION}.linux-$(dpkg --print-architecture).tar.gz" | tar xz -C /usr/local
          echo "/usr/local/go/bin" >> $GITHUB_PATH
      - uses: actions/cache@v4
        with:
          path: /github/home/.cache/ccache
          key: ccache-${{ runner.os }}-${{ runner.arch }}-${{ matrix.preset }}-${{ needs.changes.outputs.vendorsha }}
      - name: Build llama-server
        run: |
          cmake -S llama/server --preset cpu ${{ matrix.flags }}
          cmake --build build/llama-server-cpu -- -l $(nproc)

  windows:
    needs: [changes]
    if: needs.changes.outputs.changed == 'True'
    strategy:
      matrix:
        include:
          - preset: CPU
          - preset: CUDA
            install: https://developer.download.nvidia.com/compute/cuda/13.0.0/local_installers/cuda_13.0.0_windows.exe
            flags: '-DCMAKE_CUDA_ARCHITECTURES=80'
            cuda-components:
              - '"cudart"'
              - '"nvcc"'
              - '"cublas"'
              - '"cublas_dev"'
              - '"crt"'
              - '"nvvm"'
              - '"nvptxcompiler"'
            cuda-version: '13.0'
          - preset: ROCm
            install: https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-26.Q1-Win11-For-HIP.exe
            rocm-version: '7.1'
            flags: '-DAMDGPU_TARGETS=gfx1010 -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_C_FLAGS="-parallel-jobs=4 -Wno-ignored-attributes -Wno-deprecated-pragma" -DCMAKE_CXX_FLAGS="-parallel-jobs=4 -Wno-ignored-attributes -Wno-deprecated-pragma"'
          - preset: Vulkan
            install: https://sdk.lunarg.com/sdk/download/1.4.321.1/windows/vulkansdk-windows-X64-1.4.321.1.exe
          - preset: 'MLX CUDA 13'
            install: https://developer.download.nvidia.com/compute/cuda/13.0.0/local_installers/cuda_13.0.0_windows.exe
            cudnn-install: https://developer.download.nvidia.com/compute/cudnn/redist/cudnn/windows-x86_64/cudnn-windows-x86_64-9.18.1.3_cuda13-archive.zip
            flags: '-DCMAKE_CUDA_ARCHITECTURES=80'
            cuda-components:
              - '"cudart"'
              - '"nvcc"'
              - '"cublas"'
              - '"cublas_dev"'
              - '"cufft"'
              - '"cufft_dev"'
              - '"nvrtc"'
              - '"nvrtc_dev"'
              - '"crt"'
              - '"nvvm"'
              - '"nvptxcompiler"'
            cuda-version: '13.0'
    runs-on: windows
    steps:
      - run: |
          choco install -y --no-progress ccache ninja
          if (Get-Command ccache -ErrorAction SilentlyContinue) {
            ccache -o cache_dir=${{ github.workspace }}\.ccache
          }
      - if: matrix.preset == 'CUDA' || matrix.preset == 'ROCm' || matrix.preset == 'Vulkan' || matrix.preset == 'MLX CUDA 13'
        id: cache-install
        uses: actions/cache/restore@v4
        with:
          path: |
            C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA
            C:\Program Files\AMD\ROCm
            C:\VulkanSDK
            C:\Program Files\NVIDIA\CUDNN
          key: ${{ matrix.install }}-${{ matrix.cudnn-install }}
      - if: matrix.preset == 'CUDA' || matrix.preset == 'MLX CUDA 13'
        name: Install CUDA ${{ matrix.cuda-version }}
        run: |
          $ErrorActionPreference = "Stop"
          if ("${{ steps.cache-install.outputs.cache-hit }}" -ne 'true') {
            Invoke-WebRequest -Uri "${{ matrix.install }}" -OutFile "install.exe"
            $subpackages = @(${{ join(matrix.cuda-components, ', ') }}) | Foreach-Object {"${_}_${{ matrix.cuda-version }}"}
            Start-Process -FilePath .\install.exe -ArgumentList (@("-s") + $subpackages) -NoNewWindow -Wait
          }

          $cudaPath = (Resolve-Path "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\*").path
          echo "$cudaPath\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
      - if: matrix.preset == 'ROCm'
        name: Install ROCm ${{ matrix.rocm-version }}
        run: |
          $ErrorActionPreference = "Stop"
          if ("${{ steps.cache-install.outputs.cache-hit }}" -ne 'true') {
            Invoke-WebRequest -Uri "${{ matrix.install }}" -OutFile "install.exe"
            Start-Process -FilePath .\install.exe -ArgumentList '-install' -NoNewWindow -Wait
          }

          $hipPath = (Resolve-Path "C:\Program Files\AMD\ROCm\*").path
          echo "$hipPath\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
          echo "CC=$hipPath\bin\clang.exe" | Out-File -FilePath $env:GITHUB_ENV -Append
          echo "CXX=$hipPath\bin\clang++.exe" | Out-File -FilePath $env:GITHUB_ENV -Append
          echo "HIPCXX=$hipPath\bin\clang++.exe" | Out-File -FilePath $env:GITHUB_ENV -Append
          echo "HIP_PLATFORM=amd" | Out-File -FilePath $env:GITHUB_ENV -Append
          echo "CMAKE_PREFIX_PATH=$hipPath" | Out-File -FilePath $env:GITHUB_ENV -Append
      - if: matrix.preset == 'Vulkan'
        name: Install Vulkan ${{ matrix.rocm-version }}
        run: |
          $ErrorActionPreference = "Stop"
          if ("${{ steps.cache-install.outputs.cache-hit }}" -ne 'true') {
            Invoke-WebRequest -Uri "${{ matrix.install }}" -OutFile "install.exe"
            Start-Process -FilePath .\install.exe -ArgumentList "-c","--am","--al","in" -NoNewWindow -Wait
          }

          $vulkanPath = (Resolve-Path "C:\VulkanSDK\*").path
          echo "$vulkanPath\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
          echo "VULKAN_SDK=$vulkanPath" >> $env:GITHUB_ENV
      - if: matrix.preset == 'MLX CUDA 13'
        name: Install cuDNN for MLX
        run: |
          $ErrorActionPreference = "Stop"
          $cudnnRoot = "C:\Program Files\NVIDIA\CUDNN"
          if ("${{ steps.cache-install.outputs.cache-hit }}" -ne 'true') {
            Invoke-WebRequest -Uri "${{ matrix.cudnn-install }}" -OutFile "cudnn.zip"
            Expand-Archive -Path cudnn.zip -DestinationPath cudnn-extracted
            $cudnnDir = (Get-ChildItem -Path cudnn-extracted -Directory)[0].FullName
            New-Item -ItemType Directory -Force -Path $cudnnRoot
            Copy-Item -Path "$cudnnDir\*" -Destination "$cudnnRoot\" -Recurse
          }

          echo "CUDNN_ROOT_DIR=$cudnnRoot" | Out-File -FilePath $env:GITHUB_ENV -Append
          echo "CUDNN_INCLUDE_PATH=$cudnnRoot\include" | Out-File -FilePath $env:GITHUB_ENV -Append
          echo "CUDNN_LIBRARY_PATH=$cudnnRoot\lib\x64" | Out-File -FilePath $env:GITHUB_ENV -Append
          echo "$cudnnRoot\bin\x64" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
      - if: ${{ !cancelled() && steps.cache-install.outputs.cache-hit != 'true' }}
        uses: actions/cache/save@v4
        with:
          path: |
            C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA
            C:\Program Files\AMD\ROCm
            C:\VulkanSDK
            C:\Program Files\NVIDIA\CUDNN
          key: ${{ matrix.install }}-${{ matrix.cudnn-install }}
      - uses: actions/checkout@v4
      - uses: actions/cache@v4
        with:
          path: ${{ github.workspace }}\.ccache
          key: ccache-${{ runner.os }}-${{ runner.arch }}-${{ matrix.preset }}-${{ needs.changes.outputs.vendorsha }}
      - name: Build llama-server
        if: matrix.preset != 'MLX CUDA 13'
        run: |
          Import-Module 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise\Common7\Tools\Microsoft.VisualStudio.DevShell.dll'
          Enter-VsDevShell -VsInstallPath 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise' -SkipAutomaticLocation  -DevCmdArguments '-arch=x64 -no_logo'
          cmake -S llama\server --preset cpu ${{ matrix.flags }}
          cmake --build build\llama-server-cpu -- -l $([Environment]::ProcessorCount)
        env:
          CMAKE_GENERATOR: Ninja
      - name: Build MLX
        if: matrix.preset == 'MLX CUDA 13'
        run: |
          Import-Module 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise\Common7\Tools\Microsoft.VisualStudio.DevShell.dll'
          Enter-VsDevShell -VsInstallPath 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise' -SkipAutomaticLocation  -DevCmdArguments '-arch=x64 -no_logo'
          cmake --preset "${{ matrix.preset }}" ${{ matrix.flags }}
          cmake --build --preset "${{ matrix.preset }}" -- -l $([Environment]::ProcessorCount)
        env:
          CMAKE_GENERATOR: Ninja

  go_mod_tidy:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - name: check that 'go mod tidy' is clean
        run: go mod tidy --diff || (echo "Please run 'go mod tidy'." && exit 1)

  test:
    strategy:
      matrix:
        os: [ubuntu-latest, macos-latest, windows-latest]
    runs-on: ${{ matrix.os }}
    env:
      CGO_ENABLED: '1'
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-go@v5
        with:
          go-version-file: 'go.mod'
          cache-dependency-path: |
            go.sum
            LLAMA_CPP_VERSION
      - uses: actions/setup-node@v4
        with:
          node-version: '20'
      - name: Install UI dependencies
        working-directory: ./app/ui/app
        run: npm ci
      - name: Install tscriptify
        run: |
          go install github.com/tkrajina/typescriptify-golang-structs/tscriptify@latest
      - name: Run UI tests
        if: ${{ startsWith(matrix.os, 'ubuntu') }}
        working-directory: ./app/ui/app
        run: npm test
      - name: Run go generate
        run: go generate ./...

      - name: go test
        if: always()
        run: go test -count=1 -benchtime=1x ./...

      - uses: golangci/golangci-lint-action@v9
        with:
          only-new-issues: true