name: CI

on:
  workflow_dispatch: # allows manual triggering
    inputs:
      create_release:
        description: "Create new release"
        required: true
        type: boolean
  push:
    branches:
      - master
      - ci
    paths:
      [
        ".github/workflows/**",
        "**/CMakeLists.txt",
        "**/Makefile",
        "**/*.h",
        "**/*.hpp",
        "**/*.c",
        "**/*.cpp",
        "**/*.cu",
      ]
  pull_request:
    types: [opened, synchronize, reopened]
    paths:
      [
        "**/CMakeLists.txt",
        "**/Makefile",
        "**/*.h",
        "**/*.hpp",
        "**/*.c",
        "**/*.cpp",
        "**/*.cu",
      ]

env:
  BRANCH_NAME: ${{ github.head_ref || github.ref_name }}

jobs:
  ubuntu-latest-cmake:
    runs-on: ubuntu-latest

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v3
        with:
          submodules: recursive

      - name: Dependencies
        id: depends
        run: |
          sudo apt-get update
          sudo apt-get install build-essential

      - name: Build
        id: cmake_build
        run: |
          mkdir build
          cd build
          cmake .. -DGGML_AVX2=ON -DSD_BUILD_SHARED_LIBS=ON
          cmake --build . --config Release

      - name: Get commit hash
        id: commit
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: pr-mpt/actions-commit-hash@v2

      - name: Fetch system info
        id: system-info
        run: |
          echo "CPU_ARCH=`uname -m`" >> "$GITHUB_OUTPUT"
          echo "OS_NAME=`lsb_release -s -i`" >> "$GITHUB_OUTPUT"
          echo "OS_VERSION=`lsb_release -s -r`" >> "$GITHUB_OUTPUT"
          echo "OS_TYPE=`uname -s`" >> "$GITHUB_OUTPUT"

      - name: Pack artifacts
        id: pack_artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        run: |
          cp ggml/LICENSE ./build/bin/ggml.txt
          cp LICENSE ./build/bin/stable-diffusion.cpp.txt
          zip -j sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-${{ steps.system-info.outputs.OS_TYPE }}-${{ steps.system-info.outputs.OS_NAME }}-${{ steps.system-info.outputs.OS_VERSION }}-${{ steps.system-info.outputs.CPU_ARCH }}.zip ./build/bin/*

      - name: Upload artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: actions/upload-artifact@v4
        with:
          name: sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-${{ steps.system-info.outputs.OS_TYPE }}-${{ steps.system-info.outputs.OS_NAME }}-${{ steps.system-info.outputs.OS_VERSION }}-${{ steps.system-info.outputs.CPU_ARCH }}.zip
          path: |
            sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-${{ steps.system-info.outputs.OS_TYPE }}-${{ steps.system-info.outputs.OS_NAME }}-${{ steps.system-info.outputs.OS_VERSION }}-${{ steps.system-info.outputs.CPU_ARCH }}.zip

  macOS-latest-cmake:
    runs-on: macos-latest

    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v3
        with:
          submodules: recursive

      - name: Dependencies
        id: depends
        run: |
          brew install zip

      - name: Build
        id: cmake_build
        run: |
          sysctl -a
          mkdir build
          cd build
          cmake .. -DGGML_AVX2=ON -DCMAKE_OSX_ARCHITECTURES="arm64;x86_64" -DSD_BUILD_SHARED_LIBS=ON
          cmake --build . --config Release

      - name: Get commit hash
        id: commit
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: pr-mpt/actions-commit-hash@v2

      - name: Fetch system info
        id: system-info
        run: |
          echo "CPU_ARCH=`uname -m`" >> "$GITHUB_OUTPUT"
          echo "OS_NAME=`sw_vers -productName`" >> "$GITHUB_OUTPUT"
          echo "OS_VERSION=`sw_vers -productVersion`" >> "$GITHUB_OUTPUT"
          echo "OS_TYPE=`uname -s`" >> "$GITHUB_OUTPUT"

      - name: Pack artifacts
        id: pack_artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        run: |
          cp ggml/LICENSE ./build/bin/ggml.txt
          cp LICENSE ./build/bin/stable-diffusion.cpp.txt
          zip -j sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-${{ steps.system-info.outputs.OS_TYPE }}-${{ steps.system-info.outputs.OS_NAME }}-${{ steps.system-info.outputs.OS_VERSION }}-${{ steps.system-info.outputs.CPU_ARCH }}.zip ./build/bin/*

      - name: Upload artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: actions/upload-artifact@v4
        with:
          name: sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-${{ steps.system-info.outputs.OS_TYPE }}-${{ steps.system-info.outputs.OS_NAME }}-${{ steps.system-info.outputs.OS_VERSION }}-${{ steps.system-info.outputs.CPU_ARCH }}.zip
          path: |
            sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-${{ steps.system-info.outputs.OS_TYPE }}-${{ steps.system-info.outputs.OS_NAME }}-${{ steps.system-info.outputs.OS_VERSION }}-${{ steps.system-info.outputs.CPU_ARCH }}.zip

  windows-latest-cmake:
    runs-on: windows-2025

    env:
      VULKAN_VERSION: 1.4.328.1

    strategy:
      matrix:
        include:
          - build: "noavx"
            defines: "-DGGML_NATIVE=OFF -DGGML_AVX=OFF -DGGML_AVX2=OFF -DGGML_FMA=OFF -DSD_BUILD_SHARED_LIBS=ON"
          - build: "avx2"
            defines: "-DGGML_NATIVE=OFF -DGGML_AVX2=ON -DSD_BUILD_SHARED_LIBS=ON"
          - build: "avx"
            defines: "-DGGML_NATIVE=OFF -DGGML_AVX=ON -DGGML_AVX2=OFF -DSD_BUILD_SHARED_LIBS=ON"
          - build: "avx512"
            defines: "-DGGML_NATIVE=OFF -DGGML_AVX512=ON -DGGML_AVX=ON -DGGML_AVX2=ON -DSD_BUILD_SHARED_LIBS=ON"
          - build: "cuda12"
            defines: "-DSD_CUDA=ON -DSD_BUILD_SHARED_LIBS=ON -DCMAKE_CUDA_ARCHITECTURES=90;89;86;80;75"
          - build: 'vulkan'
            defines: "-DSD_VULKAN=ON -DSD_BUILD_SHARED_LIBS=ON"
    steps:
      - name: Clone
        id: checkout
        uses: actions/checkout@v3
        with:
          submodules: recursive

      - name: Install cuda-toolkit
        id: cuda-toolkit
        if: ${{ matrix.build == 'cuda12' }}
        uses: Jimver/cuda-toolkit@v0.2.19
        with:
          cuda: "12.6.2"
          method: "network"
          sub-packages: '["nvcc", "cudart", "cublas", "cublas_dev", "thrust", "visual_studio_integration"]'

      - name: Install Vulkan SDK
        id: get_vulkan
        if: ${{ matrix.build == 'vulkan' }}
        run: |
          curl.exe -o $env:RUNNER_TEMP/VulkanSDK-Installer.exe -L "https://sdk.lunarg.com/sdk/download/${env:VULKAN_VERSION}/windows/vulkansdk-windows-X64-${env:VULKAN_VERSION}.exe"
          & "$env:RUNNER_TEMP\VulkanSDK-Installer.exe" --accept-licenses --default-answer --confirm-command install
          Add-Content $env:GITHUB_ENV "VULKAN_SDK=C:\VulkanSDK\${env:VULKAN_VERSION}"
          Add-Content $env:GITHUB_PATH "C:\VulkanSDK\${env:VULKAN_VERSION}\bin"

      - name: Build
        id: cmake_build
        run: |
          mkdir build
          cd build
          cmake .. ${{ matrix.defines }}
          cmake --build . --config Release

      - name: Check AVX512F support
        id: check_avx512f
        if: ${{ matrix.build == 'avx512' }}
        continue-on-error: true
        run: |
          cd build
          $vcdir = $(vswhere -latest -products * -requires Microsoft.VisualStudio.Component.VC.Tools.x86.x64 -property installationPath)
          $msvc = $(join-path $vcdir $('VC\Tools\MSVC\'+$(gc -raw $(join-path $vcdir 'VC\Auxiliary\Build\Microsoft.VCToolsVersion.default.txt')).Trim()))
          $cl =  $(join-path $msvc 'bin\Hostx64\x64\cl.exe')
          echo 'int main(void){unsigned int a[4];__cpuid(a,7);return !(a[1]&65536);}' >> avx512f.c
          & $cl /O2 /GS- /kernel avx512f.c /link /nodefaultlib /entry:main
          .\avx512f.exe && echo "AVX512F: YES" && ( echo HAS_AVX512F=1 >> $env:GITHUB_ENV ) || echo "AVX512F: NO"

      - name: Get commit hash
        id: commit
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: pr-mpt/actions-commit-hash@v2

      - name: Pack artifacts
        id: pack_artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        run: |
          $filePath = ".\build\bin\Release\*"
          if (Test-Path $filePath) {
            echo "Exists at path $filePath"
            Copy-Item ggml/LICENSE .\build\bin\Release\ggml.txt
            Copy-Item LICENSE .\build\bin\Release\stable-diffusion.cpp.txt
          } elseif (Test-Path ".\build\bin\stable-diffusion.dll") {
          $filePath = ".\build\bin\*"
            echo "Exists at path $filePath"
            Copy-Item ggml/LICENSE .\build\bin\ggml.txt
            Copy-Item LICENSE .\build\bin\stable-diffusion.cpp.txt
          } else {
            ls .\build\bin
            throw "Can't find stable-diffusion.dll"
          }
          7z a sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-${{ matrix.build }}-x64.zip $filePath

      - name: Copy and pack Cuda runtime
        id: pack_cuda_runtime
        if: ${{ matrix.build == 'cuda12' && (github.event_name == 'push' && github.ref == 'refs/heads/master' || github.event.inputs.create_release == 'true') }}
        run: |
          echo "Cuda install location: ${{steps.cuda-toolkit.outputs.CUDA_PATH}}"
          $dst='.\build\bin\cudart\'
          robocopy "${{steps.cuda-toolkit.outputs.CUDA_PATH}}\bin" $dst cudart64_*.dll cublas64_*.dll cublasLt64_*.dll
          7z a cudart-sd-bin-win-cu12-x64.zip $dst\*

      - name: Upload Cuda runtime
        if: ${{ matrix.build == 'cuda12' && (github.event_name == 'push' && github.ref == 'refs/heads/master' || github.event.inputs.create_release == 'true') }}
        uses: actions/upload-artifact@v4
        with:
          name: sd-cudart-sd-bin-win-cu12-x64.zip
          path: |
            cudart-sd-bin-win-cu12-x64.zip

      - name: Upload artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: actions/upload-artifact@v4
        with:
          name: sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-${{ matrix.build }}-x64.zip
          path: |
            sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-${{ matrix.build }}-x64.zip

  windows-latest-cmake-hip:
    runs-on: windows-2022

    env:
      HIPSDK_INSTALLER_VERSION: "25.Q3"
      GPU_TARGETS: "gfx1151;gfx1200;gfx1201;gfx1100;gfx1101;gfx1102;gfx1030;gfx1031;gfx1032"

    steps:
      - uses: actions/checkout@v3
        with:
          submodules: recursive

      - name: Cache ROCm Installation
        id: cache-rocm
        uses: actions/cache@v4
        with:
          path: C:\Program Files\AMD\ROCm
          key: rocm-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ runner.os }}

      - name: ccache
        uses: ggml-org/ccache-action@v1.2.16
        with:
          key: windows-latest-cmake-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-x64
          evict-old-files: 1d

      - name: Install ROCm
        if: steps.cache-rocm.outputs.cache-hit != 'true'
        run: |
          $ErrorActionPreference = "Stop"
          write-host "Downloading AMD HIP SDK Installer"
          Invoke-WebRequest -Uri "https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-${{ env.HIPSDK_INSTALLER_VERSION }}-WinSvr2022-For-HIP.exe" -OutFile "${env:RUNNER_TEMP}\rocm-install.exe"
          write-host "Installing AMD HIP SDK"
          $proc = Start-Process "${env:RUNNER_TEMP}\rocm-install.exe" -ArgumentList '-install' -NoNewWindow -PassThru
          $completed = $proc.WaitForExit(600000)
          if (-not $completed) {
              Write-Error "ROCm installation timed out after 10 minutes. Killing the process"
              $proc.Kill()
              exit 1
          }
          if ($proc.ExitCode -ne 0) {
              Write-Error "ROCm installation failed with exit code $($proc.ExitCode)"
              exit 1
          }
          write-host "Completed AMD HIP SDK installation"

      - name: Verify ROCm
        run: |
          # Find and test ROCm installation
          $clangPath = Get-ChildItem 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | Select-Object -First 1
          if (-not $clangPath) {
            Write-Error "ROCm installation not found"
            exit 1
          }
          & $clangPath.FullName --version
          # Set HIP_PATH environment variable for later steps
          echo "HIP_PATH=$(Resolve-Path 'C:\Program Files\AMD\ROCm\*\bin\clang.exe' | split-path | split-path)" >> $env:GITHUB_ENV

      - name: Build
        run: |
          mkdir build
          cd build
          $env:CMAKE_PREFIX_PATH="${env:HIP_PATH}"
          cmake .. `
            -G "Unix Makefiles" `
            -DSD_HIPBLAS=ON `
            -DSD_BUILD_SHARED_LIBS=ON `
            -DGGML_NATIVE=OFF `
            -DCMAKE_C_COMPILER=clang `
            -DCMAKE_CXX_COMPILER=clang++ `
            -DCMAKE_BUILD_TYPE=Release `
            -DGPU_TARGETS="${{ env.GPU_TARGETS }}"
          cmake --build . --config Release --parallel ${env:NUMBER_OF_PROCESSORS}

      - name: Get commit hash
        id: commit
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: pr-mpt/actions-commit-hash@v2

      - name: Pack artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        run: |
          md "build\bin\rocblas\library\"
          md "build\bin\hipblaslt\library"
          cp "${env:HIP_PATH}\bin\hipblas.dll" "build\bin\"
          cp "${env:HIP_PATH}\bin\hipblaslt.dll" "build\bin\"
          cp "${env:HIP_PATH}\bin\rocblas.dll" "build\bin\"
          cp "${env:HIP_PATH}\bin\rocblas\library\*" "build\bin\rocblas\library\"
          cp "${env:HIP_PATH}\bin\hipblaslt\library\*" "build\bin\hipblaslt\library\"
          7z a sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-rocm-x64.zip .\build\bin\*

      - name: Upload artifacts
        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
        uses: actions/upload-artifact@v4
        with:
          name: sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-rocm-x64.zip
          path: |
            sd-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-rocm-x64.zip

  release:
    if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}

    runs-on: ubuntu-latest

    needs:
      - ubuntu-latest-cmake
      - macOS-latest-cmake
      - windows-latest-cmake
      - windows-latest-cmake-hip

    steps:
      - name: Clone
        uses: actions/checkout@v3
        with:
          fetch-depth: 0

      - name: Download artifacts
        id: download-artifact
        uses: actions/download-artifact@v4
        with:
          path: ./artifact
          pattern: sd-*
          merge-multiple: true

      - name: Get commit count
        id: commit_count
        run: |
          echo "count=$(git rev-list --count HEAD)" >> $GITHUB_OUTPUT

      - name: Get commit hash
        id: commit
        uses: pr-mpt/actions-commit-hash@v2

      - name: Create release
        id: create_release
        if: ${{ github.event_name == 'workflow_dispatch' || github.ref_name == 'master' }}
        uses: anzz1/action-create-release@v1
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        with:
          tag_name: ${{ format('{0}-{1}-{2}', env.BRANCH_NAME, steps.commit_count.outputs.count, steps.commit.outputs.short) }}

      - name: Upload release
        id: upload_release
        if: ${{ github.event_name == 'workflow_dispatch' || github.ref_name == 'master' }}
        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('./artifact')) {
              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(`./artifact/${file}`)
                });
              }
            }