FastDeploy/.github/workflows/_xpu_4cards_case_test.yml

name: xpu_4cards_case_test

on:
  workflow_call:
    inputs:
      DOCKER_IMAGE:
        description: "Build Images"
        required: true
        type: string
        default: "ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:ci"
      FASTDEPLOY_ARCHIVE_URL:
        description: "URL of the compressed FastDeploy code archive."
        required: true
        type: string
      FASTDEPLOY_WHEEL_URL:
        description: "URL of the compressed FastDeploy whl ."
        required: true
        type: string
      FD_VERSION:
        description: "FastDeploy Package Version"
        required: false
        type: string
        default: ""
      PADDLEVERSION:
        description: "Paddle Version Build Use"
        required: false
        type: string
        default: ""
      PADDLE_WHL_URL:
        description: "Paddle Wheel Package URL"
        required: false
        type: string
        default: ""
      MODEL_PATH:
        description: "MODEL Dir Use"
        required: true
        type: string
        default: ""
    secrets:
      github-token:
        required: true

jobs:
  check_bypass:
    uses: ./.github/workflows/check-bypass.yml
    secrets:
      github-token: ${{ secrets.github-token }}
    with:
      workflow-name: xpu_4cards_test

  run_xpu_4cards_cases:
    runs-on: [self-hosted, XPU-P800-4Cards]
    needs: check_bypass
    if: ${{ inputs.FASTDEPLOY_WHEEL_URL != '' && needs.check_bypass.outputs.can-skip != 'true' }}
    timeout-minutes: 60
    steps:
      - name: Print current runner name
        run: |
          echo "Current runner name: ${{ runner.name }}"
      - name: Code Prepare
        shell: bash
        env:
          docker_image: ${{ inputs.DOCKER_IMAGE }}
          fd_archive_url: ${{ inputs.FASTDEPLOY_ARCHIVE_URL }}
          fd_wheel_url: ${{ inputs.FASTDEPLOY_WHEEL_URL }}
          model_path: ${{ inputs.MODEL_PATH }}
        run: |
            set -x
            REPO="https://github.com/${{ github.repository }}.git"
            FULL_REPO="${{ github.repository }}"
            REPO_NAME="${FULL_REPO##*/}"
            BASE_BRANCH="${{ github.base_ref }}"
            docker pull ${docker_image} || true
            # Clean the repository directory before starting
            docker run --rm --net=host -v $(pwd):/workspace -w /workspace \
            -e "REPO_NAME=${REPO_NAME}" \
            ${docker_image} /bin/bash -c '
              CLEAN_RETRIES=3
              CLEAN_COUNT=0

              while [ $CLEAN_COUNT -lt $CLEAN_RETRIES ]; do
                echo "Attempt $((CLEAN_COUNT+1)) to remove ${REPO_NAME}* ..."
                rm -rf "${REPO_NAME}"* || true
                sleep 2

                # Check if anything matching ${REPO_NAME}* still exists
                if ! ls "${REPO_NAME}"* >/dev/null 2>&1; then
                  echo "All ${REPO_NAME}* removed successfully"
                  break
                fi

                CLEAN_COUNT=$((CLEAN_COUNT + 1))
              done

              if ls "${REPO_NAME}"* >/dev/null 2>&1; then
                echo "ERROR: Failed to clean ${REPO_NAME}* after multiple attempts"
                ls -ld "${REPO_NAME}"*
                exit 1
              fi
            '

            wget -q --no-proxy ${fd_archive_url}
            tar -xf FastDeploy.tar.gz
            rm -rf FastDeploy.tar.gz
            cd FastDeploy
            git config --global user.name "FastDeployCI"
            git config --global user.email "fastdeploy_ci@example.com"
            git log -n 3 --oneline

      - name: Run CI unittest
        env:
          docker_image: ${{ inputs.DOCKER_IMAGE }}
          fd_archive_url: ${{ inputs.FASTDEPLOY_ARCHIVE_URL }}
          fd_wheel_url: ${{ inputs.FASTDEPLOY_WHEEL_URL }}
          model_path: ${{ inputs.MODEL_PATH }}
        run: |
          runner_name="${{ runner.name }}"
          last_char="${runner_name: -1}"

          if [[ "$last_char" == "1" ]]; then
            xpu_id="4"
          else
            xpu_id="0"
          fi
          PARENT_DIR=$(dirname "$WORKSPACE")
          echo "PARENT_DIR:$PARENT_DIR"
          docker run --rm --net=host --cap-add=SYS_PTRACE --privileged --shm-size=64G  \
          -v $(pwd):/workspace -w /workspace \
          -v "/ssd3:/ssd3" \
          -e "MODEL_PATH=${model_path}" \
          -e "FASTDEPLOY_ARCHIVE_URL=${fd_archive_url}" \
          -e "FASTDEPLOY_WHEEL_URL=${fd_wheel_url}" \
          -e "PADDLEVERSION=${PADDLEVERSION}" \
          -e "PADDLE_WHL_URL=${PADDLE_WHL_URL}" \
          -e "http_proxy=$(git config --global --get http.proxy)" \
          -e "https_proxy=$(git config --global --get https.proxy)" \
          -e "no_proxy=bcebos.com,mirrors.tuna.tsinghua.edu.cn,127.0.0.1,localhost" \
          -e "XPU_ID=${xpu_id}" \
          ${docker_image} /bin/bash -c '
          echo "安装lsof工具..."
          apt install -y lsof

          # 设置XPU_VISIBLE_DEVICES
          if [[ "$XPU_ID" == "0" ]]; then
              export XPU_VISIBLE_DEVICES="0,1,2,3"
          else
              export XPU_VISIBLE_DEVICES="4,5,6,7"
          fi
          echo "XPU_VISIBLE_DEVICES=$XPU_VISIBLE_DEVICES"

          # 下载和安装xre
          echo "下载和安装xre..."
          mkdir -p /workspace/deps
          cd /workspace/deps
          if [ ! -d "xre" ]; then
              wget -q https://klx-sdk-release-public.su.bcebos.com/xre/kl3-release/5.0.21.21/xre-Linux-x86_64-5.0.21.21.tar.gz
              tar -zxf xre-Linux-x86_64-5.0.21.21.tar.gz && mv xre-Linux-x86_64-5.0.21.21 xre
          fi
          cd -
          export PATH=/workspace/deps/xre/bin:$PATH

          # 重启XPU卡
          echo "重启XPU卡..."
          xpu-smi -r -i $XPU_VISIBLE_DEVICES
          xpu-smi
          set -e
          git config --global --add safe.directory /workspace/FastDeploy
          cd FastDeploy
          python -m pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
          python -m pip install -r requirements.txt
          echo "安装PaddlePaddle..."
          # 针对不同分支和tag使用不同的PaddlePaddle安装包
          if [[ "${PADDLE_WHL_URL}" != "" ]];then
            python -m pip uninstall paddlepaddle-xpu fastdeploy-xpu -y
            python -m pip install ${PADDLE_WHL_URL}
          elif [[ "${PADDLEVERSION}" != "" ]];then
            python -m pip uninstall paddlepaddle-xpu fastdeploy-xpu -y
            python -m pip install paddlepaddle-xpu==${PADDLEVERSION} -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
          else
            python -m pip uninstall paddlepaddle-xpu fastdeploy-xpu -y
            python -m pip install --pre paddlepaddle-xpu -i https://www.paddlepaddle.org.cn/packages/nightly/xpu-p800/
          fi
          echo "安装上游任务编译的fastdeploy-xpu..."
          python -m pip install ${FASTDEPLOY_WHEEL_URL}
          rm -rf fastdeploy
          python -m pip install ${FASTDEPLOY_WHEEL_URL} --no-deps --target=/workspace/FastDeploy
          echo "============================安装测试依赖============================"
          python -m pip install openai -U
          python -m pip install pytest
          python -m pip install pytest-timeout
          unset http_proxy
          unset https_proxy
          echo "============================开始运行pytest测试============================"
          export PYTHONPATH=/workspace/FastDeploy/
          export PYTHONPATH=$(pwd)/tests/xpu_ci:$PYTHONPATH
          mkdir -p case_logs
          set +e
          python -m pytest -v -s --tb=short tests/xpu_ci/4cards_cases/
          exit_code=$?
          set -e

          # 修改case_logs权限，确保Docker外部的runner用户可以读取并上传
          chmod -R a+rX case_logs/ 2>/dev/null || true

          if [ $exit_code -eq 0 ]; then
              echo "============================4卡cases测试通过!============================"
              exit $exit_code
          else
              echo "============================4卡cases测试失败,请检查日志!============================"
              exit $exit_code
          fi
          '

      - name: Upload case logs
        if: always()
        uses: actions/upload-artifact@v6
        with:
          name: xpu-4cards-case-logs
          path: FastDeploy/case_logs/
          retention-days: 7
          if-no-files-found: ignore