diff --git a/.github/workflows/release-docker-amd-nightly.yml b/.github/workflows/release-docker-amd-nightly.yml index 8923facad..aa97c2edd 100644 --- a/.github/workflows/release-docker-amd-nightly.yml +++ b/.github/workflows/release-docker-amd-nightly.yml @@ -15,11 +15,11 @@ concurrency: jobs: publish: if: github.repository == 'sgl-project/sglang' - runs-on: amd-docker + runs-on: amd-docker-scale environment: 'prod' strategy: matrix: - rocm_version: ['6.3.0'] + gpu_arch: ['gfx942', 'gfx950'] build_type: ['all', 'srt'] steps: - name: Checkout repository @@ -29,17 +29,6 @@ jobs: run: | echo "DATE=$(date +%Y%m%d)" >> $GITHUB_ENV - - name: Free disk space - uses: jlumbroso/free-disk-space@main - with: - tool-cache: false - docker-images: false - android: true - dotnet: true - haskell: true - large-packages: true - swap-storage: false - - name: Login to Docker Hub uses: docker/login-action@v2 with: @@ -48,6 +37,19 @@ jobs: - name: Build and Push run: | + version=$(cat python/sglang/version.py | cut -d'"' -f2) + + if [ "${{ matrix.gpu_arch }}" = "gfx942" ]; then + rocm_tag="rocm630-mi30x" + elif [ "${{ matrix.gpu_arch }}" = "gfx950" ]; then + rocm_tag="rocm700-mi35x" + else + echo "Unsupported gfx arch" + exit 1 + fi + + tag=v${version}-${rocm_tag} + if [ "${{ matrix.build_type }}" = "all" ]; then tag_suffix="" elif [ "${{ matrix.build_type }}" = "srt" ]; then @@ -57,10 +59,5 @@ jobs: exit 1 fi - docker build . -f docker/Dockerfile.rocm --build-arg BUILD_TYPE=${{ matrix.build_type }} -t rocm/sgl-dev:${{ env.DATE }}${tag_suffix} --no-cache - docker push rocm/sgl-dev:${{ env.DATE }}${tag_suffix} - - - name: "Remove docker image" - run: | - sudo rm -rf /var/lib/docker - sudo systemctl restart docker + docker build . -f docker/Dockerfile.rocm --build-arg BUILD_TYPE=${{ matrix.build_type }} --build-arg GPU_ARCH=${{ matrix.gpu_arch }} -t rocm/sgl-dev:${tag}-${{ env.DATE }}${tag_suffix} --no-cache + docker push rocm/sgl-dev:${tag}-${{ env.DATE }}${tag_suffix} diff --git a/.github/workflows/release-docker-amd.yml b/.github/workflows/release-docker-amd.yml index f93ae3178..07582243f 100644 --- a/.github/workflows/release-docker-amd.yml +++ b/.github/workflows/release-docker-amd.yml @@ -10,27 +10,16 @@ on: jobs: publish: if: github.repository == 'sgl-project/sglang' - runs-on: amd-docker + runs-on: amd-docker-scale environment: 'prod' strategy: matrix: - rocm_version: ['6.3.0'] + gpu_arch: ['gfx942', 'gfx950'] build_type: ['all', 'srt'] steps: - name: Checkout repository uses: actions/checkout@v4 - - name: Free disk space - uses: jlumbroso/free-disk-space@main - with: - tool-cache: false - docker-images: false - android: true - dotnet: true - haskell: true - large-packages: true - swap-storage: false - - name: Login to Docker Hub uses: docker/login-action@v2 with: @@ -41,10 +30,12 @@ jobs: run: | version=$(cat python/sglang/version.py | cut -d'"' -f2) - if [ "${{ matrix.rocm_version }}" = "6.3.0" ]; then - rocm_tag="rocm630" + if [ "${{ matrix.gpu_arch }}" = "gfx942" ]; then + rocm_tag="rocm630-mi30x" + elif [ "${{ matrix.gpu_arch }}" = "gfx950" ]; then + rocm_tag="rocm700-mi35x" else - echo "Unsupported ROCm version" + echo "Unsupported gfx arch" exit 1 fi @@ -59,5 +50,5 @@ jobs: exit 1 fi - docker build . -f docker/Dockerfile.rocm --build-arg BUILD_TYPE=${{ matrix.build_type }} -t lmsysorg/sglang:${tag}${tag_suffix} --no-cache + docker build . -f docker/Dockerfile.rocm --build-arg BUILD_TYPE=${{ matrix.build_type }} --build-arg GPU_ARCH=${{ matrix.gpu_arch }} -t lmsysorg/sglang:${tag}${tag_suffix} --no-cache docker push lmsysorg/sglang:${tag}${tag_suffix}