sgl-project--sglang/.github/workflows/release-docker-amd-nightly.yml

name: Release Docker Images Nightly ROCm7.0 (AMD)
on:
  workflow_dispatch:
  schedule:
    - cron: '0 12 * * *'

concurrency:
  # A PR number if a pull request and otherwise the commit hash. This cancels
  # queued and in-progress runs for the same PR (presubmit) or commit
  # (postsubmit). The workflow name is prepended to avoid conflicts between
  # different workflows.
  group: ${{ github.workflow }}-${{ github.event.number || github.sha }}
  cancel-in-progress: true

jobs:
  publish:
    if: github.repository == 'sgl-project/sglang'
    runs-on: amd-docker-scale
    environment: 'prod'
    strategy:
      fail-fast: false
      matrix:
        gpu_arch: ['gfx942', 'gfx950']
        build_type: ['all']
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          fetch-depth: 0  # Required for git describe to find tags

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: "3.10"

      - name: "Set Date"
        run: |
          echo "DATE=$(date +%Y%m%d)" >> $GITHUB_ENV

      - name: Get version from latest tag
        id: version
        run: |
          # Use the shared helper so stable/post releases sort above rc tags.
          VERSION=$(python3 python/tools/get_version_tag.py --tag-only | sed 's/^v//')

          if [ -z "$VERSION" ]; then
            echo "::error::Could not determine version from git tags"
            exit 1
          fi

          # Get short commit hash of current HEAD
          COMMIT_HASH=$(git rev-parse --short HEAD)

          # Compose pretend version for setuptools_scm: e.g., 0.5.8.dev20260129+g1a2b3c4
          PRETEND_VERSION="${VERSION}.dev${{ env.DATE }}+g${COMMIT_HASH}"

          echo "version=${VERSION}" >> $GITHUB_OUTPUT
          echo "pretend_version=${PRETEND_VERSION}" >> $GITHUB_OUTPUT
          echo "Detected version: ${VERSION}"
          echo "Pretend version for pip: ${PRETEND_VERSION}"

      - name: Login to Docker Hub (AMD)
        uses: docker/login-action@v2
        with:
          username: ${{ secrets.DOCKERHUB_AMD_USERNAME }}
          password: ${{ secrets.DOCKERHUB_AMD_TOKEN }}

      - name: Build and Push to rocm/sgl-dev
        run: |
          version=${{ steps.version.outputs.version }}
          pretend_version=${{ steps.version.outputs.pretend_version }}
          echo "Version: ${version}"
          echo "Pretend version: ${pretend_version}"

          if [ "${{ matrix.gpu_arch }}" = "gfx942" ]; then
            rocm_tag="rocm700-mi30x"
          elif [ "${{ matrix.gpu_arch }}" = "gfx950" ]; then
            rocm_tag="rocm700-mi35x"
          else
            echo "Unsupported gfx arch"
            exit 1
          fi

          tag=v${version}-${rocm_tag}
          echo "IMAGE_TAG=${tag}-${{ env.DATE }}" >> $GITHUB_ENV

          # remove --build-arg NIC_BACKEND=ainic for auto detection nic support in mori
          # UBUNTU_MIRROR forces apt over HTTPS to dodge port-80 reachability flakes
          # to Canonical's archive.ubuntu.com mirror IPs from the amd-docker-scale runner.
          docker build . -f docker/rocm.Dockerfile --build-arg SGL_BRANCH=${{ github.ref_name }} --build-arg BUILD_TYPE=${{ matrix.build_type }} --build-arg GPU_ARCH=${{ matrix.gpu_arch }} --build-arg ENABLE_MORI=1 --build-arg ENABLE_NIXL=1 --build-arg SETUPTOOLS_SCM_PRETEND_VERSION=${pretend_version} --build-arg UBUNTU_MIRROR=https://archive.ubuntu.com -t rocm/sgl-dev:${tag}-${{ env.DATE }} --no-cache
          docker push rocm/sgl-dev:${tag}-${{ env.DATE }}

      # Persist the tag right after rocm/sgl-dev push succeeds so the local
      # registry mirror can run even if a later step in this job (lmsys push)
      # fails. By default this step only runs when the previous step succeeded,
      # so the artifact only exists when an image actually landed on Docker Hub.
      - name: Save published image tag
        run: |
          mkdir -p image-tag
          echo "${{ env.IMAGE_TAG }}" > "image-tag/${{ matrix.gpu_arch }}.txt"

      - name: Upload image tag artifact
        uses: actions/upload-artifact@v4
        with:
          name: image-tag-${{ matrix.gpu_arch }}
          path: image-tag/${{ matrix.gpu_arch }}.txt
          retention-days: 1

      - name: Login to Docker Hub (lmsys)
        uses: docker/login-action@v2
        with:
          username: ${{ secrets.DOCKERHUB_USERNAME }}
          password: ${{ secrets.DOCKERHUB_TOKEN }}

      - name: Push to lmsysorg/sglang-rocm
        run: |
          docker tag rocm/sgl-dev:${{ env.IMAGE_TAG }} lmsysorg/sglang-rocm:${{ env.IMAGE_TAG }}
          docker push lmsysorg/sglang-rocm:${{ env.IMAGE_TAG }}

  # Mirror the freshly published rocm/sgl-dev image to the in-network Docker
  # registry so AMD CI runners can pull without hitting Docker Hub rate limits.
  # The tag is read verbatim from the publish job's artifact so this job uses
  # exactly the same tag that publish pushed (only the registry prefix differs).
  # `!cancelled()` lets us still mirror successful matrix legs when other legs
  # of publish failed; legs without an artifact will fail at download and be
  # the only ones marked red.
  push_local_registry:
    if: ${{ !cancelled() && github.repository == 'sgl-project/sglang' }}
    runs-on: linux-mi300-1gpu-sglang
    environment: 'prod'
    needs: publish
    strategy:
      fail-fast: false
      matrix:
        gpu_arch: ['gfx942', 'gfx950']
    steps:
      - name: Download image tag artifact
        uses: actions/download-artifact@v4
        with:
          name: image-tag-${{ matrix.gpu_arch }}

      - name: Read image tag
        run: |
          image_tag=$(tr -d '[:space:]' < "${{ matrix.gpu_arch }}.txt")
          if [ -z "${image_tag}" ]; then
            echo "::error::Image tag artifact is empty"
            exit 1
          fi
          echo "IMAGE_TAG=${image_tag}" >> $GITHUB_ENV
          echo "Resolved IMAGE_TAG=${image_tag}"

      - name: Login to Docker Hub (AMD)
        uses: docker/login-action@v2
        with:
          username: ${{ secrets.DOCKERHUB_AMD_USERNAME }}
          password: ${{ secrets.DOCKERHUB_AMD_TOKEN }}

      - name: Mirror rocm/sgl-dev to local registry
        run: |
          src="rocm/sgl-dev:${{ env.IMAGE_TAG }}"
          dst="10.44.14.109:5000/rocm/sgl-dev:${{ env.IMAGE_TAG }}"
          docker pull "${src}"
          docker tag "${src}" "${dst}"
          docker push "${dst}"

  # Temporarily disable docker cache seeding until performant storage is in place
  # cache:
  #   if: false
  #   # if: always() && github.repository == 'sgl-project/sglang'
  #   runs-on: linux-mi300-gpu-1
  #   environment: 'prod'
  #   needs: publish
  #   strategy:
  #     fail-fast: false
  #     matrix:
  #       gpu_arch: ['gfx942']
  #       build_type: ['all']
  #   steps:
  #     - name: Checkout repository
  #       uses: actions/checkout@v4
  #       with:
  #         fetch-depth: 0  # Required for git describe to find tags

  #     - name: "Set Date"
  #       run: |
  #         echo "DATE=$(date +%Y%m%d)" >> $GITHUB_ENV

  #     - name: Get version from latest tag
  #       id: version
  #       run: |
  #         # Use the shared helper so stable/post releases sort above rc tags.
  #         VERSION=$(python3 python/tools/get_version_tag.py --tag-only | sed 's/^v//')

  #         if [ -z "$VERSION" ]; then
  #           echo "::error::Could not determine version from git tags"
  #           exit 1
  #         fi

  #         echo "version=${VERSION}" >> $GITHUB_OUTPUT
  #         echo "Detected version: ${VERSION}"

  #     - name: Login to Docker Hub
  #       uses: docker/login-action@v2
  #       with:
  #         username: ${{ secrets.DOCKERHUB_AMD_USERNAME }}
  #         password: ${{ secrets.DOCKERHUB_AMD_TOKEN }}

  #     - name: Pull and Save Docker Image to Cache
  #       run: |
  #         set -euxo pipefail

  #         version=${{ steps.version.outputs.version }}
  #         echo "Version: ${version}"

  #         if [ "${{ matrix.gpu_arch }}" = "gfx942" ]; then
  #           rocm_tag="rocm700-mi30x"
  #         else
  #           echo "Unsupported gfx arch"
  #           exit 1
  #         fi

  #         tag=v${version}-${rocm_tag}

  #         if [ "${{ matrix.build_type }}" = "all" ]; then
  #           tag_suffix=""
  #         else
  #           echo "Unsupported build type"
  #           exit 1
  #         fi

  #         image="rocm/sgl-dev:${tag}-${{ env.DATE }}${tag_suffix}"

  #         # Determine target cache file name based on ROCm variant
  #         if [[ "${rocm_tag}" == rocm700* ]]; then
  #           final_path="/home/runner/sgl-data/docker/image-700.tar"
  #         else
  #           echo "Unexpected ROCm tag: ${rocm_tag}"
  #           exit 1
  #         fi

  #         tmp_path="${final_path}.tmp"

  #         echo "Pulling image: ${image}"
  #         docker pull "${image}"

  #         echo "Saving to temp file: ${tmp_path}"
  #         docker save "${image}" -o "${tmp_path}"

  #         echo "Moving to final path: ${final_path}"
  #         mv -f "${tmp_path}" "${final_path}"

  #         echo "Cache populated successfully at ${final_path}"