Split workflow for releasing runtime docker (#21563)

.github/workflows/release-docker-runtime.yml

@@ -0,0 +1,309 @@
+name: Release Docker Runtime Images
+#
+# This workflow builds and publishes runtime Docker images (production-optimized, ~50% smaller):
+#   - lmsysorg/sglang:v{version}-runtime, lmsysorg/sglang:latest-runtime
+#   - lmsysorg/sglang:v{version}-cu130-runtime, lmsysorg/sglang:latest-cu130-runtime
+#
+on:
+  push:
+    tags:
+      - "v[0-9]+.*"
+  workflow_dispatch:
+    inputs:
+      version:
+        description: "Version to build (without v prefix, e.g., 0.5.7)"
+        required: true
+
+jobs:
+  publish-x86:
+    if: github.repository == 'sgl-project/sglang'
+    environment: "prod"
+    strategy:
+      matrix:
+        variant:
+          - cuda_version: "12.9.1"
+            build_type: "all"
+            grace_blackwell: 0
+    runs-on: x64-docker-build-node
+    steps:
+      - name: Delete huge unnecessary tools folder
+        run: rm -rf /opt/hostedtoolcache
+
+      - 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: 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: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Get version from tag
+        id: version
+        run: |
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            VERSION="${{ github.event.inputs.version }}"
+          else
+            # Extract version from tag (e.g., v0.5.7 -> 0.5.7)
+            VERSION="${GITHUB_REF_NAME#v}"
+          fi
+
+          # Validate version format
+          if [ -z "$VERSION" ]; then
+            echo "::error::Version is empty"
+            exit 1
+          fi
+          if ! echo "$VERSION" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::Invalid version format: $VERSION (expected: X.Y.Z)"
+            exit 1
+          fi
+
+          echo "version=${VERSION}" >> $GITHUB_OUTPUT
+
+      - name: Build and Push AMD64 Runtime
+        run: |
+          version=${{ steps.version.outputs.version }}
+
+          docker buildx build \
+            --target runtime \
+            --platform linux/amd64 \
+            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
+            -f docker/Dockerfile \
+            --build-arg CUDA_VERSION=${{ matrix.variant.cuda_version }} \
+            --build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
+            --build-arg GRACE_BLACKWELL=${{ matrix.variant.grace_blackwell }} \
+            --build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
+            --build-arg SGL_VERSION=${version} \
+            --metadata-file /tmp/metadata-cu129-runtime.json \
+            --no-cache \
+            .
+
+          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu129-runtime.json'))['containerimage.digest'])")
+          echo "Pushed digest: ${DIGEST}"
+          echo "${DIGEST}" > /tmp/digest-cu129-amd64-runtime.txt
+
+      - name: Build and Push AMD64 Runtime (CUDA 13)
+        run: |
+          version=${{ steps.version.outputs.version }}
+
+          docker buildx build \
+            --target runtime \
+            --platform linux/amd64 \
+            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
+            -f docker/Dockerfile \
+            --build-arg CUDA_VERSION=13.0.1 \
+            --build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
+            --build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
+            --build-arg GRACE_BLACKWELL=0 \
+            --build-arg SGL_VERSION=${version} \
+            --metadata-file /tmp/metadata-cu130-runtime.json \
+            --no-cache \
+            .
+
+          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu130-runtime.json'))['containerimage.digest'])")
+          echo "Pushed digest: ${DIGEST}"
+          echo "${DIGEST}" > /tmp/digest-cu130-amd64-runtime.txt
+
+      - name: Upload digests
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-amd64
+          path: /tmp/digest-*.txt
+          retention-days: 1
+
+  publish-arm64:
+    if: github.repository == 'sgl-project/sglang'
+    environment: "prod"
+    strategy:
+      matrix:
+        variant:
+          - cuda_version: "12.9.1"
+            build_type: "all"
+            grace_blackwell: 1
+    runs-on: arm-docker-build-node
+    steps:
+      - name: Delete huge unnecessary tools folder
+        run: rm -rf /opt/hostedtoolcache
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - 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: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Get version from tag
+        id: version
+        run: |
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            VERSION="${{ github.event.inputs.version }}"
+          else
+            # Extract version from tag (e.g., v0.5.7 -> 0.5.7)
+            VERSION="${GITHUB_REF_NAME#v}"
+          fi
+
+          # Validate version format
+          if [ -z "$VERSION" ]; then
+            echo "::error::Version is empty"
+            exit 1
+          fi
+          if ! echo "$VERSION" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::Invalid version format: $VERSION (expected: X.Y.Z)"
+            exit 1
+          fi
+
+          echo "version=${VERSION}" >> $GITHUB_OUTPUT
+
+      - name: Build and Push ARM64 Runtime
+        run: |
+          version=${{ steps.version.outputs.version }}
+
+          docker buildx build \
+            --target runtime \
+            --platform linux/arm64 \
+            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
+            -f docker/Dockerfile \
+            --build-arg CUDA_VERSION=${{ matrix.variant.cuda_version }} \
+            --build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
+            --build-arg GRACE_BLACKWELL=${{ matrix.variant.grace_blackwell }} \
+            --build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
+            --build-arg SGL_VERSION=${version} \
+            --metadata-file /tmp/metadata-cu129-runtime.json \
+            --no-cache \
+            .
+
+          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu129-runtime.json'))['containerimage.digest'])")
+          echo "Pushed digest: ${DIGEST}"
+          echo "${DIGEST}" > /tmp/digest-cu129-arm64-runtime.txt
+
+      - name: Build and Push ARM64 Runtime (CUDA 13)
+        run: |
+          version=${{ steps.version.outputs.version }}
+
+          docker buildx build \
+            --target runtime \
+            --platform linux/arm64 \
+            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
+            -f docker/Dockerfile \
+            --build-arg CUDA_VERSION=13.0.1 \
+            --build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
+            --build-arg GRACE_BLACKWELL=1 \
+            --build-arg SGL_VERSION=${version} \
+            --metadata-file /tmp/metadata-cu130-runtime.json \
+            --no-cache \
+            .
+
+          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu130-runtime.json'))['containerimage.digest'])")
+          echo "Pushed digest: ${DIGEST}"
+          echo "${DIGEST}" > /tmp/digest-cu130-arm64-runtime.txt
+
+      - name: Upload digests
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-arm64
+          path: /tmp/digest-*.txt
+          retention-days: 1
+
+  create-manifests:
+    runs-on: ubuntu-22.04
+    needs: [publish-x86, publish-arm64]
+    if: github.repository == 'sgl-project/sglang'
+    environment: "prod"
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - 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: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Get version from tag
+        id: version
+        run: |
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            VERSION="${{ github.event.inputs.version }}"
+          else
+            # Extract version from tag (e.g., v0.5.7 -> 0.5.7)
+            VERSION="${GITHUB_REF_NAME#v}"
+          fi
+
+          # Validate version format
+          if [ -z "$VERSION" ]; then
+            echo "::error::Version is empty"
+            exit 1
+          fi
+          if ! echo "$VERSION" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::Invalid version format: $VERSION (expected: X.Y.Z)"
+            exit 1
+          fi
+
+          echo "version=${VERSION}" >> $GITHUB_OUTPUT
+
+      - name: Download amd64 digests
+        uses: actions/download-artifact@v4
+        with:
+          name: digests-amd64
+          path: /tmp/digests/amd64
+
+      - name: Download arm64 digests
+        uses: actions/download-artifact@v4
+        with:
+          name: digests-arm64
+          path: /tmp/digests/arm64
+
+      - name: Create multi-arch manifests
+        run: |
+          version=${{ steps.version.outputs.version }}
+
+          CU129_AMD64_RT=$(cat /tmp/digests/amd64/digest-cu129-amd64-runtime.txt)
+          CU130_AMD64_RT=$(cat /tmp/digests/amd64/digest-cu130-amd64-runtime.txt)
+          CU129_ARM64_RT=$(cat /tmp/digests/arm64/digest-cu129-arm64-runtime.txt)
+          CU130_ARM64_RT=$(cat /tmp/digests/arm64/digest-cu130-arm64-runtime.txt)
+
+          # Create versioned runtime manifest
+          docker buildx imagetools create \
+            -t lmsysorg/sglang:v${version}-runtime \
+            lmsysorg/sglang@${CU129_AMD64_RT} \
+            lmsysorg/sglang@${CU129_ARM64_RT}
+
+          # Create latest runtime manifest
+          docker buildx imagetools create \
+            -t lmsysorg/sglang:latest-runtime \
+            lmsysorg/sglang@${CU129_AMD64_RT} \
+            lmsysorg/sglang@${CU129_ARM64_RT}
+
+          # Create versioned CUDA 13 runtime manifest
+          docker buildx imagetools create \
+            -t lmsysorg/sglang:v${version}-cu130-runtime \
+            lmsysorg/sglang@${CU130_AMD64_RT} \
+            lmsysorg/sglang@${CU130_ARM64_RT}
+
+          # Create latest CUDA 13 runtime manifest
+          docker buildx imagetools create \
+            -t lmsysorg/sglang:latest-cu130-runtime \
+            lmsysorg/sglang@${CU130_AMD64_RT} \
+            lmsysorg/sglang@${CU130_ARM64_RT}

.github/workflows/release-docker.yml

@@ -1,15 +1,9 @@
 name: Release Docker Images
 #
-# This workflow builds and publishes both framework and runtime Docker images:
+# This workflow builds and publishes framework Docker images (full development environment):
-#
-# Framework images (full development environment):
 #   - lmsysorg/sglang:v{version}, lmsysorg/sglang:latest
 #   - lmsysorg/sglang:v{version}-cu130, lmsysorg/sglang:latest-cu130
 #
-# Runtime images (production-optimized, ~50% smaller):
-#   - lmsysorg/sglang:v{version}-runtime, lmsysorg/sglang:latest-runtime
-#   - lmsysorg/sglang:v{version}-cu130-runtime, lmsysorg/sglang:latest-cu130-runtime
-#
 on:
   push:
     tags:
@@ -102,28 +96,6 @@ jobs:
           echo "Pushed digest: ${DIGEST}"
           echo "${DIGEST}" > /tmp/digest-cu129-amd64-framework.txt
 
-      - name: Build and Push AMD64 Runtime
-        run: |
-          version=${{ steps.version.outputs.version }}
-
-          docker buildx build \
-            --target runtime \
-            --platform linux/amd64 \
-            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
-            -f docker/Dockerfile \
-            --build-arg CUDA_VERSION=${{ matrix.variant.cuda_version }} \
-            --build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
-            --build-arg GRACE_BLACKWELL=${{ matrix.variant.grace_blackwell }} \
-            --build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
-            --build-arg SGL_VERSION=${version} \
-            --metadata-file /tmp/metadata-cu129-runtime.json \
-            --no-cache \
-            .
-
-          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu129-runtime.json'))['containerimage.digest'])")
-          echo "Pushed digest: ${DIGEST}"
-          echo "${DIGEST}" > /tmp/digest-cu129-amd64-runtime.txt
-
       - name: Build and Push AMD64 Framework (CUDA 13)
         run: |
           version=${{ steps.version.outputs.version }}
@@ -146,28 +118,6 @@ jobs:
           echo "Pushed digest: ${DIGEST}"
           echo "${DIGEST}" > /tmp/digest-cu130-amd64-framework.txt
 
-      - name: Build and Push AMD64 Runtime (CUDA 13)
-        run: |
-          version=${{ steps.version.outputs.version }}
-
-          docker buildx build \
-            --target runtime \
-            --platform linux/amd64 \
-            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
-            -f docker/Dockerfile \
-            --build-arg CUDA_VERSION=13.0.1 \
-            --build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
-            --build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
-            --build-arg GRACE_BLACKWELL=0 \
-            --build-arg SGL_VERSION=${version} \
-            --metadata-file /tmp/metadata-cu130-runtime.json \
-            --no-cache \
-            .
-
-          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu130-runtime.json'))['containerimage.digest'])")
-          echo "Pushed digest: ${DIGEST}"
-          echo "${DIGEST}" > /tmp/digest-cu130-amd64-runtime.txt
-
       - name: Upload digests
         uses: actions/upload-artifact@v4
         with:
@@ -245,28 +195,6 @@ jobs:
           echo "Pushed digest: ${DIGEST}"
           echo "${DIGEST}" > /tmp/digest-cu129-arm64-framework.txt
 
-      - name: Build and Push ARM64 Runtime
-        run: |
-          version=${{ steps.version.outputs.version }}
-
-          docker buildx build \
-            --target runtime \
-            --platform linux/arm64 \
-            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
-            -f docker/Dockerfile \
-            --build-arg CUDA_VERSION=${{ matrix.variant.cuda_version }} \
-            --build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
-            --build-arg GRACE_BLACKWELL=${{ matrix.variant.grace_blackwell }} \
-            --build-arg INSTALL_FLASHINFER_JIT_CACHE=1 \
-            --build-arg SGL_VERSION=${version} \
-            --metadata-file /tmp/metadata-cu129-runtime.json \
-            --no-cache \
-            .
-
-          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu129-runtime.json'))['containerimage.digest'])")
-          echo "Pushed digest: ${DIGEST}"
-          echo "${DIGEST}" > /tmp/digest-cu129-arm64-runtime.txt
-
       - name: Build and Push ARM64 Framework (CUDA 13)
         run: |
           version=${{ steps.version.outputs.version }}
@@ -289,27 +217,6 @@ jobs:
           echo "Pushed digest: ${DIGEST}"
           echo "${DIGEST}" > /tmp/digest-cu130-arm64-framework.txt
 
-      - name: Build and Push ARM64 Runtime (CUDA 13)
-        run: |
-          version=${{ steps.version.outputs.version }}
-
-          docker buildx build \
-            --target runtime \
-            --platform linux/arm64 \
-            --output type=image,name=lmsysorg/sglang,push-by-digest=true,name-canonical=true,push=true \
-            -f docker/Dockerfile \
-            --build-arg CUDA_VERSION=13.0.1 \
-            --build-arg BUILD_TYPE=${{ matrix.variant.build_type }} \
-            --build-arg GRACE_BLACKWELL=1 \
-            --build-arg SGL_VERSION=${version} \
-            --metadata-file /tmp/metadata-cu130-runtime.json \
-            --no-cache \
-            .
-
-          DIGEST=$(python3 -c "import json; print(json.load(open('/tmp/metadata-cu130-runtime.json'))['containerimage.digest'])")
-          echo "Pushed digest: ${DIGEST}"
-          echo "${DIGEST}" > /tmp/digest-cu130-arm64-runtime.txt
-
       - name: Upload digests
         uses: actions/upload-artifact@v4
         with:
@@ -373,15 +280,10 @@ jobs:
         run: |
           version=${{ steps.version.outputs.version }}
 
-          # Load all digests
           CU129_AMD64_FW=$(cat /tmp/digests/amd64/digest-cu129-amd64-framework.txt)
-          CU129_AMD64_RT=$(cat /tmp/digests/amd64/digest-cu129-amd64-runtime.txt)
           CU130_AMD64_FW=$(cat /tmp/digests/amd64/digest-cu130-amd64-framework.txt)
-          CU130_AMD64_RT=$(cat /tmp/digests/amd64/digest-cu130-amd64-runtime.txt)
           CU129_ARM64_FW=$(cat /tmp/digests/arm64/digest-cu129-arm64-framework.txt)
-          CU129_ARM64_RT=$(cat /tmp/digests/arm64/digest-cu129-arm64-runtime.txt)
           CU130_ARM64_FW=$(cat /tmp/digests/arm64/digest-cu130-arm64-framework.txt)
-          CU130_ARM64_RT=$(cat /tmp/digests/arm64/digest-cu130-arm64-runtime.txt)
 
           # Create versioned framework manifest (default)
           docker buildx imagetools create \
@@ -395,18 +297,6 @@ jobs:
             lmsysorg/sglang@${CU129_AMD64_FW} \
             lmsysorg/sglang@${CU129_ARM64_FW}
 
-          # Create versioned runtime manifest
-          docker buildx imagetools create \
-            -t lmsysorg/sglang:v${version}-runtime \
-            lmsysorg/sglang@${CU129_AMD64_RT} \
-            lmsysorg/sglang@${CU129_ARM64_RT}
-
-          # Create latest runtime manifest
-          docker buildx imagetools create \
-            -t lmsysorg/sglang:latest-runtime \
-            lmsysorg/sglang@${CU129_AMD64_RT} \
-            lmsysorg/sglang@${CU129_ARM64_RT}
-
           # Create versioned CUDA 13 framework manifest
           docker buildx imagetools create \
             -t lmsysorg/sglang:v${version}-cu130 \
@@ -418,15 +308,3 @@ jobs:
             -t lmsysorg/sglang:latest-cu130 \
             lmsysorg/sglang@${CU130_AMD64_FW} \
             lmsysorg/sglang@${CU130_ARM64_FW}
-
-          # Create versioned CUDA 13 runtime manifest
-          docker buildx imagetools create \
-            -t lmsysorg/sglang:v${version}-cu130-runtime \
-            lmsysorg/sglang@${CU130_AMD64_RT} \
-            lmsysorg/sglang@${CU130_ARM64_RT}
-
-          # Create latest CUDA 13 runtime manifest
-          docker buildx imagetools create \
-            -t lmsysorg/sglang:latest-cu130-runtime \
-            lmsysorg/sglang@${CU130_AMD64_RT} \
-            lmsysorg/sglang@${CU130_ARM64_RT}