feat: add sglanf backend to release workflow

Author: denyszhak

.github/workflows/promote-to-latest.yml

@@ -5,7 +5,7 @@ on:
   workflow_dispatch:
     inputs:
       version:
-        description: 'version'
+        description: "version"
         required: true
         type: string
 
@@ -42,6 +42,11 @@ jobs:
           echo "Promoting vLLM CUDA images"
           crane tag "docker/model-runner:${{ inputs.version }}-vllm-cuda" "latest-vllm-cuda"
 
+      - name: Promote SGLang CUDA images
+        run: |
+          echo "Promoting SGLang CUDA images"
+          crane tag "docker/model-runner:${{ inputs.version }}-sglang-cuda" "latest-sglang-cuda"
+
       - name: Promote ROCm images
         run: |
           echo "Promoting ROCm images"

.github/workflows/release.yml

@@ -5,28 +5,33 @@ on:
   workflow_dispatch:
     inputs:
       pushLatest:
-        description: 'Tag images produced by this job as latest'
+        description: "Tag images produced by this job as latest"
         required: false
         type: boolean
         default: false
       releaseTag:
-        description: 'Release tag'
+        description: "Release tag"
         required: false
         type: string
         default: "test"
       llamaServerVersion:
-        description: 'llama-server version'
+        description: "llama-server version"
         required: false
         type: string
         default: "latest"
       vllmVersion:
-        description: 'vLLM version'
+        description: "vLLM version"
         required: false
         type: string
         default: "0.12.0"
+      sglangVersion:
+        description: "SGLang version"
+        required: false
+        type: string
+        default: "0.4.0"
       # This can be removed once we have llama.cpp built for MUSA and CANN.
       buildMusaCann:
-        description: 'Build MUSA and CANN images'
+        description: "Build MUSA and CANN images"
         required: false
         type: boolean
         default: false
@@ -76,6 +81,12 @@ jobs:
             echo "docker/model-runner:latest-vllm-cuda" >> "$GITHUB_OUTPUT"
           fi
           echo 'EOF' >> "$GITHUB_OUTPUT"
+          echo "sglang-cuda<<EOF" >> "$GITHUB_OUTPUT"
+          echo "docker/model-runner:${{ inputs.releaseTag }}-sglang-cuda" >> "$GITHUB_OUTPUT"
+          if [ "${{ inputs.pushLatest }}" == "true" ]; then
+            echo "docker/model-runner:latest-sglang-cuda" >> "$GITHUB_OUTPUT"
+          fi
+          echo 'EOF' >> "$GITHUB_OUTPUT"
           echo "rocm<<EOF" >> "$GITHUB_OUTPUT"
           echo "docker/model-runner:${{ inputs.releaseTag }}-rocm" >> "$GITHUB_OUTPUT"
           if [ "${{ inputs.pushLatest }}" == "true" ]; then
@@ -155,6 +166,22 @@ jobs:
           provenance: mode=max
           tags: ${{ steps.tags.outputs.vllm-cuda }}
 
+      - name: Build SGLang CUDA image
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83
+        with:
+          file: Dockerfile
+          target: final-sglang
+          platforms: linux/amd64, linux/arm64
+          build-args: |
+            "LLAMA_SERVER_VERSION=${{ inputs.llamaServerVersion }}"
+            "LLAMA_SERVER_VARIANT=cuda"
+            "BASE_IMAGE=nvidia/cuda:12.9.0-runtime-ubuntu24.04"
+            "SGLANG_VERSION=${{ inputs.sglangVersion }}"
+          push: true
+          sbom: true
+          provenance: mode=max
+          tags: ${{ steps.tags.outputs.sglang-cuda }}
+
       - name: Build ROCm image
         uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83
         with: