Build/Test workflow trigger based on file changes and job-level concurrency for SageMaker endpoint tests

.github/actions/ecr-authenticate/action.yml

@@ -2,13 +2,13 @@ name: ECR Authentication
 description: Login to ECR, if image_uri is provided pull the image onto host runner.
 
 inputs:
-  aws_region:
-    description: AWS Region for docker image repository
-    required: true
-  aws_account_id:
+  aws-account-id:
     description: AWS Account ID for docker image registry
     required: true
-  image_uri:
+  aws-region:
+    description: AWS Region for docker image repository
+    required: true
+  image-uri:
     description: Docker image URI to pull from ECR
     required: false
 

.github/workflows/pr-sglang.yml

@@ -19,37 +19,51 @@ env:
   PYTHON_VERSION: "py312"
   CUDA_VERSION: "cu129"
   OS_VERSION: "ubuntu22.04"
+  PROD_SAGEMAKER_IMAGE: sglang:0.5.5-gpu-py312-cu129-ubuntu22.04-sagemaker
   FORCE_COLOR: "1"
 
 jobs:
   check-changes:
     runs-on: ubuntu-latest
     outputs:
-      sglang-sagemaker: ${{ steps.changes.outputs.sglang-sagemaker }}
+      build-change: ${{ steps.changes.outputs.build-change }}
+      test-change: ${{ steps.changes.outputs.test-change }}
     steps:
-      - uses: actions/checkout@v5
-      - uses: actions/setup-python@v6
+      - name: Checkout DLC source
+        uses: actions/checkout@v5
+
+      - name: Setup python
+        uses: actions/setup-python@v6
         with:
           python-version: "3.12"
-      - uses: pre-commit/action@v3.0.1
+
+      - name: Run pre-commit
+        uses: pre-commit/action@v3.0.1
         with:
           extra_args: --all-files
+
       - name: Detect file changes
         id: changes
         uses: dorny/paths-filter@v3
         with:
           filters: |
-            sglang-sagemaker:
-              - "docker/sglang/Dockerfile"
+            build-change:
+              - "docker/sglang/**"
+              - "scripts/sglang/**"
+              - "scripts/common/**"
+              - "scripts/telemetry/**"
+              - ".github/workflows/pr-sglang*"
+            test-change:
+              - "test/sglang/**"
 
   build-sglang-image:
     needs: [check-changes]
-    if: needs.check-changes.outputs.sglang-sagemaker == 'true'
+    if: needs.check-changes.outputs.build-change == 'true'
     runs-on:
       - codebuild-runner-${{ github.run_id }}-${{ github.run_attempt }}
         fleet:x86-build-runner
     outputs:
-      image-uri: ${{ steps.image-uri-build.outputs.IMAGE_URI }}
+      ci-image: ${{ steps.image-uri-build.outputs.IMAGE_URI }}
     steps:
       - uses: actions/checkout@v5
       - run: .github/scripts/runner_setup.sh
@@ -58,16 +72,16 @@ jobs:
       - name: ECR login
         uses: ./.github/actions/ecr-authenticate
         with:
-          aws_region: ${{ vars.AWS_REGION }}
-          aws_account_id: ${{ vars.AWS_ACCOUNT_ID }}
+          aws-account-id: ${{ vars.AWS_ACCOUNT_ID }}
+          aws-region: ${{ vars.AWS_REGION }}
 
       - name: Resolve image URI for build
         id: image-uri-build
         run: |
           IMAGE_URI=${{ vars.AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_REGION }}.amazonaws.com/ci:sglang-${{ env.SGLANG_VERSION }}-gpu-${{ env.PYTHON_VERSION }}-${{ env.CUDA_VERSION }}-${{ env.OS_VERSION }}-sagemaker-pr-${{ github.event.pull_request.number }}
-          echo "Image URI to build: $IMAGE_URI"
-          echo "IMAGE_URI=$IMAGE_URI" >> $GITHUB_ENV
-          echo "IMAGE_URI=$IMAGE_URI" >> $GITHUB_OUTPUT
+          echo "Image URI to build: ${IMAGE_URI}"
+          echo "IMAGE_URI=${IMAGE_URI}" >> ${GITHUB_ENV}
+          echo "IMAGE_URI=${IMAGE_URI}" >> ${GITHUB_OUTPUT}
 
       - name: Build image
         run: |
@@ -86,145 +100,37 @@ jobs:
           docker push ${IMAGE_URI}
           docker rmi ${IMAGE_URI}
 
-  sglang-local-benchmark-test:
-    needs: [build-sglang-image]
-    if: needs.build-sglang-image.result == 'success'
-    runs-on:
-      - codebuild-runner-${{ github.run_id }}-${{ github.run_attempt }}
-        fleet:x86-g6xl-runner
+  set-test-environment:
+    needs: [check-changes, build-sglang-image]
+    runs-on: ubuntu-latest
+    outputs:
+      aws-account-id: ${{ steps.set-env.outputs.AWS_ACCOUNT_ID }}
+      image-uri: ${{ steps.set-env.outputs.IMAGE_URI }}
+      sglang-version: ${{ steps.set-env.outputs.SGLANG_VERSION }}
     steps:
-      - name: Checkout DLC source
-        uses: actions/checkout@v5
+      - name: Checkout code
+        uses: actions/checkout@v4
 
-      - name: Container pull
-        uses: ./.github/actions/ecr-authenticate
-        with:
-          aws_region: ${{ vars.AWS_REGION }}
-          aws_account_id: ${{ vars.AWS_ACCOUNT_ID }}
-          image_uri: ${{ needs.build-sglang-image.outputs.image-uri }}
-
-      - name: Setup for SGLang datasets
+      - name: Set test environment
+        id: set-env
         run: |
-          mkdir -p /tmp/sglang/dataset
-          if [ ! -f /tmp/sglang/dataset/ShareGPT_V3_unfiltered_cleaned_split.json ]; then
-              echo "Downloading ShareGPT dataset..."
-              wget -P /tmp/sglang/dataset https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json
-          else
-              echo "ShareGPT dataset already exists. Skipping download."
+          if [ "${{ needs.build-sglang-image.result }}" == "success"]; then
+            AWS_ACCOUNT_ID=${{ vars.AWS_ACCOUNT_ID }}
+            IMAGE_URI=${{ needs.build-sglang-image.outputs.ci-image }}
+          elif [ "${{ needs.build-sglang-image.result }}" != "success"]; then
+            AWS_ACCOUNT_ID=${{ vars.PROD_AWS_ACCOUNT_ID }}
+            IMAGE_URI=${{ vars.PROD_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_REGION }}.amazonaws.com/${{ env.PROD_SAGEMAKER_IMAGE }}
           fi
-
-      - name: Start container
-        run: |
-          CONTAINER_ID=$(docker run -d -it --rm --gpus=all \
-            -v ${HOME}/.cache/huggingface:/root/.cache/huggingface \
-            -v /tmp/sglang/dataset:/dataset \
-            -p 30000:30000 \
-            -e SM_SGLANG_MODEL_PATH=Qwen/Qwen3-0.6B \
-            -e SM_SGLANG_REASONING_PARSER=qwen3 \
-            -e SM_SGLANG_HOST=127.0.0.1 \
-            -e SM_SGLANG_PORT=30000 \
-            -e HF_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }} \
-            ${{ needs.build-sglang-image.outputs.image-uri }})
-          echo "CONTAINER_ID=$CONTAINER_ID" >> $GITHUB_ENV
-          echo "Waiting for container startup ..."
-          sleep 60s
-          docker logs ${CONTAINER_ID}
-
-      - name: Run SGLang tests
-        run: |
-          docker exec ${CONTAINER_ID} python3 -m sglang.bench_serving \
-          --backend sglang \
-          --host 127.0.0.1 --port 30000 \
-          --num-prompts 1000 \
-          --model Qwen/Qwen3-0.6B \
-          --dataset-name sharegpt \
-          --dataset-path /dataset/ShareGPT_V3_unfiltered_cleaned_split.json
-
-      - name: Cleanup container and images
-        if: always()
-        uses: ./.github/actions/container-cleanup
-        with:
-          container_id: ${{ env.CONTAINER_ID }}
-
-  sglang-lang-test:
-    needs: [build-sglang-image]
-    if: needs.build-sglang-image.result == 'success'
-    runs-on:
-      - codebuild-runner-${{ github.run_id }}-${{ github.run_attempt }}
-        fleet:x86-g6exl-runner
-    steps:
-      - name: Checkout DLC source
-        uses: actions/checkout@v5
-
-      - name: Container pull
-        uses: ./.github/actions/ecr-authenticate
-        with:
-          aws_region: ${{ vars.AWS_REGION }}
-          aws_account_id: ${{ vars.AWS_ACCOUNT_ID }}
-          image_uri: ${{ needs.build-sglang-image.outputs.image-uri }}
-
-      - name: Checkout SGLang tests
-        uses: actions/checkout@v5
-        with:
-          repository: sgl-project/sglang
-          ref: v${{ env.SGLANG_VERSION }}
-          path: sglang_source
-
-      - name: Start container
-        run: |
-          CONTAINER_ID=$(docker run -d -it --rm --gpus=all --entrypoint /bin/bash \
-            -v ${HOME}/.cache/huggingface:/root/.cache/huggingface \
-            -v ./sglang_source:/workdir --workdir /workdir \
-            -e HF_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }} \
-            ${{ needs.build-sglang-image.outputs.image-uri }})
-          echo "CONTAINER_ID=$CONTAINER_ID" >> $GITHUB_ENV
-
-      - name: Setup for SGLang tests
-        run: |
-          docker exec ${CONTAINER_ID} sh -c '
-            set -eux
-
-            bash scripts/ci/ci_install_dependency.sh
-          '
-
-      - name: Run SGLang tests
-        run: |
-          docker exec ${CONTAINER_ID} sh -c '
-            set -eux
-            nvidia-smi
-
-            # Frontend Test
-            cd /workdir/test/lang
-            python3 run_suite.py --suite per-commit
-          '
-
-      - name: Cleanup container and images
-        if: always()
-        uses: ./.github/actions/container-cleanup
-        with:
-          container_id: ${{ env.CONTAINER_ID }}
-
-  sglang-sagemaker-endpoint-test:
-    needs: [build-sglang-image]
-    if: needs.build-sglang-image.result == 'success'
-    runs-on:
-      - codebuild-runner-${{ github.run_id }}-${{ github.run_attempt }}
-        fleet:default-runner
-    steps:
-      - name: Checkout DLC source
-        uses: actions/checkout@v5
-
-      - run: .github/scripts/runner_setup.sh
-      - name: Install test dependencies
-        run: |
-          uv venv
-          source .venv/bin/activate
-
-          uv pip install -r test/requirements.txt
-          uv pip install -r test/sglang/sagemaker/requirements.txt
-
-      - name: Run sagemaker tests
-        run: |
-          source .venv/bin/activate
-          cd test/
-          python3 -m pytest -vs -rA --image-uri ${{ needs.build-sglang-image.outputs.image-uri }} sglang/sagemaker
+          echo IMAGE_URI=${IMAGE_URI} >> ${GITHUB_OUTPUT}
+          echo AWS_ACCOUNT_ID=${AWS_ACCOUNT_ID} >> ${GITHUB_OUTPUT}
+          echo SGLANG_VERSION=${SGLANG_VERSION} >> ${GITHUB_OUTPUT}
+
+  test-sglang-image:
+    needs: [set-test-environment]
+    if: needs.set-test-environment.result == 'success'
+    uses: ./.github/workflows/test-sglang.yml
+    with:
+      aws-account-id: ${{ needs.set-test-environment.outputs.aws-account-id }}
+      aws-region: ${{ vars.AWS_REGION }}
+      image-uri: ${{ needs.set-test-environment.outputs.image-uri }}
+      sglang-version: ${{ needs.set-test-environment.outputs.sglang-version }}