release-docker-dev.yml

name: Build and Push Development Docker Images

on:
  workflow_dispatch:
    inputs:
      pr_number:
        description: "PR number to build from (leave empty to use current branch)"
        required: false
        default: ""
      tag:
        description: "Custom tag suffix (overrides pr_number in tag). E.g. 'my-test' → dev-x86-my-test, dev-cu13-my-test, etc."
        required: false
        default: ""
  schedule:
    - cron: "0 0 * * *"

concurrency:
  group: release-docker-dev-${{ inputs.tag || inputs.pr_number || 'nightly' }}
  cancel-in-progress: true

jobs:
  build-dev:
    if: ${{ github.repository == 'sgl-project/sglang' }}
    runs-on: ${{ matrix.runner }}
    strategy:
      matrix:
        include:
          - runner: x64-docker-build-node
            platform: linux/amd64
            build_type: all
            grace_blackwell: 0
            arch_tag: x86
            version: 12.9.1
          - runner: arm-docker-build-node
            platform: linux/arm64
            build_type: all
            grace_blackwell: 1
            arch_tag: arm64
            version: 12.9.1
          - runner: x64-docker-build-node
            platform: linux/amd64
            build_type: all
            grace_blackwell: 0
            arch_tag: x86-cu13
            version: 13.0.1
          - runner: arm-docker-build-node
            platform: linux/arm64
            build_type: all
            grace_blackwell: 1
            arch_tag: arm64-cu13
            version: 13.0.1
    steps:
      - name: Delete huge unnecessary tools folder
        run: rm -rf /opt/hostedtoolcache

      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          ref: ${{ inputs.pr_number && format('refs/pull/{0}/head', inputs.pr_number) || github.ref }}

      - name: Free disk space
        uses: jlumbroso/free-disk-space@main
        with:
          tool-cache: true
          docker-images: true
          android: true
          dotnet: true
          haskell: true
          large-packages: true
          swap-storage: true

      - name: Prune Docker to reclaim disk space
        run: |
          docker buildx prune --filter "until=72h" -f
          docker system prune -af --filter "until=72h"
          docker volume prune -af

      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v3

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

      - name: Build and Push Dev Image
        run: |
          # Tag suffix: custom tag > pr number > none
          SUFFIX=""
          if [ -n "${{ inputs.tag }}" ]; then
            SUFFIX="-${{ inputs.tag }}"
          elif [ -n "${{ inputs.pr_number }}" ]; then
            SUFFIX="-pr-${{ inputs.pr_number }}"
          fi

          TAG="dev-${{ matrix.arch_tag }}${SUFFIX}"

          # Nightly (schedule) installs latest release; manual dispatch builds from checked-out source
          if [ "${{ github.event_name }}" = "schedule" ]; then
            SOURCE_ARG="--build-arg USE_LATEST_SGLANG=1"
          else
            SOURCE_ARG="--build-arg BRANCH_TYPE=local"
          fi

          echo "Building lmsysorg/sglang:${TAG}"

          docker buildx build \
            --platform ${{ matrix.platform }} \
            --push \
            --target framework \
            -f docker/Dockerfile \
            --build-arg CUDA_VERSION=${{ matrix.version }} \
            --build-arg BUILD_TYPE=${{ matrix.build_type }} \
            --build-arg CMAKE_BUILD_PARALLEL_LEVEL=$(nproc) \
            --build-arg GRACE_BLACKWELL=${{ matrix.grace_blackwell }} \
            ${SOURCE_ARG} \
            --build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
            -t lmsysorg/sglang:${TAG} \
            --no-cache \
            .

  create-manifests:
    runs-on: ubuntu-22.04
    needs: [build-dev]
    if: ${{ github.repository == 'sgl-project/sglang' }}
    strategy:
      matrix:
        variant:
          - base: dev
            x86: x86
            arm64: arm64
          - base: dev-cu13
            x86: x86-cu13
            arm64: arm64-cu13
    steps:
      - uses: docker/setup-buildx-action@v3

      - uses: docker/login-action@v2
        with:
          username: ${{ secrets.DOCKERHUB_USERNAME }}
          password: ${{ secrets.DOCKERHUB_TOKEN }}

      - name: Create multi-arch manifest
        run: |
          SUFFIX=""
          if [ -n "${{ inputs.tag }}" ]; then
            SUFFIX="-${{ inputs.tag }}"
          elif [ -n "${{ inputs.pr_number }}" ]; then
            SUFFIX="-pr-${{ inputs.pr_number }}"
          fi

          TAG="${{ matrix.variant.base }}${SUFFIX}"
          X86_TAG="dev-${{ matrix.variant.x86 }}${SUFFIX}"
          ARM64_TAG="dev-${{ matrix.variant.arm64 }}${SUFFIX}"

          # For nightly (no suffix), also stamp a dated tag
          EXTRA_TAG=""
          if [ -z "${SUFFIX}" ]; then
            SHORT_SHA="${{ github.sha }}"
            EXTRA_TAG="-t lmsysorg/sglang:nightly-${TAG}-$(date +%Y%m%d)-${SHORT_SHA:0:8}"
          fi

          docker buildx imagetools create \
            -t lmsysorg/sglang:${TAG} \
            ${EXTRA_TAG} \
            lmsysorg/sglang:${X86_TAG} \
            lmsysorg/sglang:${ARM64_TAG}

          echo "✓ Published lmsysorg/sglang:${TAG}"

      - name: Cleanup Old Nightly Builds
        if: ${{ !inputs.tag && !inputs.pr_number }}
        run: |
          TOKEN=$(curl -s -H "Content-Type: application/json" \
            -X POST -d '{"username": "${{ secrets.DOCKERHUB_USERNAME }}", "password": "${{ secrets.DOCKERHUB_TOKEN }}"}' \
            https://hub.docker.com/v2/users/login/ | jq -r .token)

          TAGS_RESPONSE=$(curl -s -H "Authorization: JWT $TOKEN" \
            "https://hub.docker.com/v2/repositories/lmsysorg/sglang/tags/?page_size=100")

          TAGS=$(echo "$TAGS_RESPONSE" | jq -r \
            '.results[] | select(.name | test("^nightly-${{ matrix.variant.base }}-[0-9]")) | "\(.last_updated)|\(.name)"' \
            | sort -r | cut -d'|' -f2)

          TAG_COUNT=$(echo "$TAGS" | wc -l)
          if [ "$TAG_COUNT" -gt 14 ]; then
            echo "Found $TAG_COUNT nightly builds, keeping only the 14 most recent"
            TAGS_TO_DELETE=$(echo "$TAGS" | tail -n +15)
            for tag in $TAGS_TO_DELETE; do
              echo "Deleting tag: $tag"
              curl -X DELETE -H "Authorization: JWT $TOKEN" \
                "https://hub.docker.com/v2/repositories/lmsysorg/sglang/tags/$tag/"
            done
          else
            echo "Only $TAG_COUNT nightly builds found, no cleanup needed"
          fi