name: Publish Release

on:
  workflow_run:
    workflows:
      - Release
    types:
      - completed
    branches:
      - master

run-name: "Publish ${{ github.event.workflow_run.display_title }}"

cache-mode: none
permissions:
  actions: read
  contents: read

env:
  GH_TOKEN: ${{ github.token }}
  BRANCH_NAME: master

jobs:
  publish:
    if: ${{ github.event.workflow_run.conclusion == 'success' }}

    # Fine-grained permission
    # https://docs.github.com/en/actions/security-for-github-actions/security-guides/automatic-token-authentication#modifying-the-permissions-for-the-github_token
    permissions:
        actions: read
        contents: write # for creating release
        id-token: write
        attestations: write

    runs-on: ubuntu-latest

    outputs:
      should_release: ${{ steps.check.outputs.should_release }}
      tag_name: ${{ steps.tag.outputs.name }}

    steps:
      - id: check
        env:
          COMMIT_MESSAGE: ${{ github.event.workflow_run.head_commit.message }}
        run: |
          if echo "$COMMIT_MESSAGE" | grep -q '\[no release\]'; then
            echo "should_release=false" >> $GITHUB_OUTPUT
          else
            echo "should_release=true" >> $GITHUB_OUTPUT
          fi

      - name: Clone
        if: ${{ steps.check.outputs.should_release == 'true' }}
        id: checkout
        uses: actions/checkout@v6
        with:
          ref: ${{ github.event.workflow_run.head_sha }}
          fetch-depth: 0
          ssh-key: ${{ secrets.DEPLOY_KEY_RELEASE }}

      - name: Determine tag name
        if: ${{ steps.check.outputs.should_release == 'true' }}
        id: tag
        uses: ./.github/actions/get-tag-name

      - name: Download artifacts
        if: ${{ steps.check.outputs.should_release == 'true' }}
        id: download-artifact
        uses: actions/download-artifact@v8
        with:
          path: ./artifact
          run-id: ${{ github.event.workflow_run.id }}
          github-token: ${{ github.token }}
          merge-multiple: true
          skip-decompress: true

      - name: Merge artifacts
        if: ${{ steps.check.outputs.should_release == 'true' }}
        id: move_artifacts
        run: |
          mkdir -p release

          # the windows-cpu zip contains the full toolset (llama-server with the embedded
          # UI, ggml-cpu) - inject it into the other windows zips so that every archive
          # ships the same binaries, only with a different backend library on top
          echo "Injecting windows-cpu binaries (llama-server + CPU backend) into the backend zips..."
          for arch in x64 arm64; do
            cpu_zip="artifact/llama-bin-win-cpu-${arch}.zip"
            temp_dir=$(mktemp -d)
            echo "Extracting windows-cpu-${arch} package..."
            unzip "$cpu_zip" -d "$temp_dir"

            echo "Merging into $arch zips..."
            for target_zip in artifact/llama-bin-win-*-${arch}.zip; do
              if [[ "$target_zip" == "$cpu_zip" ]]; then
                continue
              fi
              echo "Injecting into $(basename "$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="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 other artifacts..."
          rm -f artifact/llama-ui.zip
          mv -v artifact/*.zip release
          mv -v artifact/*.tar.gz release

      - name: Download UI build
        if: ${{ steps.check.outputs.should_release == 'true' }}
        id: download_ui
        uses: actions/download-artifact@v8
        with:
          name: llama-ui.zip
          path: ./ui-dist
          run-id: ${{ github.event.workflow_run.id }}
          github-token: ${{ github.token }}

      - name: Package UI
        if: ${{ steps.check.outputs.should_release == 'true' }}
        id: package_ui
        run: |
          tar -czvf release/llama-${{ steps.tag.outputs.name }}-ui.tar.gz --transform "s,^\.,llama-${{ steps.tag.outputs.name }}," -C ./ui-dist .

      - name: Attest release artifacts
        if: ${{ steps.check.outputs.should_release == 'true' }}
        id: attest
        uses: actions/attest@v4
        with:
          subject-path: 'release/*'

      - name: Create release
        if: ${{ steps.check.outputs.should_release == 'true' }}
        id: create_release
        uses: ggml-org/action-create-release@v1
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        with:
          tag_name: ${{ steps.tag.outputs.name }}
          commitish: ${{ github.event.workflow_run.head_sha }}
          prerelease: true
          body: |
            <details open>

            ${{ github.event.workflow_run.head_commit.message }}

            </details>

            **Website:**
            - <https://llama.app>

            **Attestations:**
            - <${{ steps.attest.outputs.attestation-url }}>

            **macOS/iOS:**
            - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-macos-arm64.tar.gz)
            - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780)
            - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-macos-x64.tar.gz)
            - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-xcframework.zip)

            **Linux:**
            - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-x64.tar.gz)
            - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-arm64.tar.gz)
            - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-s390x.tar.gz)
            - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.tar.gz)
            - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-arm64.tar.gz)
            - [Ubuntu x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-12.8-x64.tar.gz) - [CUDA 12.8 libraries](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/cudart-llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-12.8-x64.tar.gz)
            - [Ubuntu x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-13.4-x64.tar.gz) - [CUDA 13.4 libraries](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/cudart-llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-13.4-x64.tar.gz)
            - [Ubuntu arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-13.4-arm64.tar.gz) - [CUDA 13.4 libraries](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/cudart-llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-13.4-arm64.tar.gz)
            - [Ubuntu x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-rocm-10.0-x64.tar.gz)
            - [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-openvino-2026.4.1-x64.tar.gz)
            - [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-sycl-fp32-x64.tar.gz)
            - [Ubuntu x64 (SYCL FP16)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-sycl-fp16-x64.tar.gz)
            - [Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-linux-arm64-snapdragon.tar.gz) - [setup guide](https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/linux.md)

            **Android:**
            - [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-android-arm64.tar.gz)
            - [Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-android-arm64-snapdragon.tar.gz) - [setup guide](https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/README.md)

            **Windows:**
            - [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-cpu-x64.zip)
            - [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-cpu-arm64.zip)
            - [Windows arm64 (OpenCL Adreno)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-opencl-adreno-arm64.zip)
            - [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/cudart-llama-bin-win-cuda-12.4-x64.zip)
            - [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-cuda-13.4-x64.zip) - [CUDA 13.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/cudart-llama-bin-win-cuda-13.4-x64.zip)
            - [Windows arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-cuda-13.4-arm64.zip) - [CUDA 13.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/cudart-llama-bin-win-cuda-13.4-arm64.zip)
            - [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-vulkan-x64.zip)
            - [Windows arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-vulkan-arm64.zip)
            - [Windows x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-openvino-2026.4.1-x64.zip)
            - [Windows x64 (SYCL)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-sycl-x64.zip)
            - [Windows x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-win-rocm-10.0-x64.zip)

            **openEuler:**
            - [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23705)
            - openEuler x86 (310p)
            - openEuler x86 (910b, ACL Graph)
            - openEuler aarch64 (310p)
            - openEuler aarch64 (910b, ACL Graph)

            **UI:**
            - [UI](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-ui.tar.gz)

      - name: Upload release
        if: ${{ steps.check.outputs.should_release == 'true' }}
        id: upload_release
        uses: actions/github-script@v8
        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' || file.endsWith('.tar.gz')) {
                console.log('uploadReleaseAsset', file);
                await github.rest.repos.uploadReleaseAsset({
                  owner: context.repo.owner,
                  repo: context.repo.repo,
                  release_id: release_id,
                  name: file,
                  data: await fs.readFileSync(`./release/${file}`)
                });
              }
            }

  ui-publish:
    if: ${{ needs.publish.outputs.should_release == 'true' }}

    needs:
      - publish

    uses: ./.github/workflows/ui-publish.yml
    with:
      version_tag: ${{ needs.publish.outputs.tag_name }}
      run_id: ${{ github.event.workflow_run.id }}
    secrets:
      hf_token: ${{ secrets.HF_TOKEN_UI_STATIC_OUTPUT }}