[Cherry-Pick][CI] Sync dev optimizations to 2.4(#7335) (#7346)

* [Cherry-Pick][CI] Sync dev optimizations to 2.4(#7335)

.github/workflows/_base_test.yml

@@ -81,7 +81,14 @@ jobs:
               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
+                echo "Attempting force cleanup with find..."
+                find /workspace -mindepth 1 -maxdepth 1 -name "${REPO_NAME}*" -type d -exec chmod -R u+rwx {} \; -exec rm -rf {} + 2>/dev/null || true
+                if ls "${REPO_NAME}"* >/dev/null 2>&1; then
+                  echo "ERROR: Force cleanup still failed"
+                  exit 1
+                else
+                  echo "Force cleanup succeeded"
+                fi
               fi
             '
 
@@ -111,7 +118,11 @@ jobs:
             exit 1
           fi
 
-          tar -xf FastDeploy.tar.gz
+          tar --no-same-owner -xf FastDeploy.tar.gz || {
+            echo "ERROR: Failed to extract archive"
+            exit 1
+          }
+
           rm -rf FastDeploy.tar.gz
           cd FastDeploy
           git config --global user.name "FastDeployCI"
@@ -182,7 +193,10 @@ jobs:
             docker rm -f ${runner_name} || true
           fi
 
-          docker run --rm --ipc=host --pid=host --net=host \
+          docker run --rm --net=host \
+          --shm-size=64g \
+          --sysctl kernel.msgmax=1048576 \
+          --sysctl kernel.msgmnb=268435456 \
           --name ${runner_name} \
           -v $(pwd):/workspace \
           -w /workspace \
@@ -197,17 +211,18 @@ jobs:
           -v "${CACHE_DIR}/.cache:/root/.cache" \
           -v "${CACHE_DIR}/ConfigDir:/root/.config" \
           -e TZ="Asia/Shanghai" \
+          -e "no_proxy=localhost,127.0.0.1,0.0.0.0,bcebos.com,.bcebos.com,bj.bcebos.com,su.bcebos.com,paddle-ci.gz.bcebos.com,apiin.im.baidu.com,baidu-int.com,.baidu.com,aliyun.com,gitee.com,pypi.tuna.tsinghua.edu.cn,.tuna.tsinghua.edu.cn" \
           --gpus '"device='"${DEVICES}"'"' ${docker_image} /bin/bash -xc '
           # Avoid using pip cache to ensure the wheel is updated to the latest version
           wget -q --no-proxy https://paddle-qa.bj.bcebos.com/paddle-pipeline/Release-TagBuild-Training-Linux-Gpu-Cuda12.6-Cudnn9.5-Trt10.5-Mkl-Avx-Gcc11-SelfBuiltPypiUse/latest/paddlepaddle_gpu-0.0.0-cp310-cp310-linux_x86_64.whl
-          python -m pip install paddlepaddle_gpu-0.0.0-cp310-cp310-linux_x86_64.whl
+          python -m pip install paddlepaddle_gpu-0.0.0-cp310-cp310-linux_x86_64.whl --extra-index-url https://www.paddlepaddle.org.cn/packages/stable/cu126/
 
           pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
 
           python -m pip install ${fastdeploy_wheel_url}
           python -m pip install pytest
 
-          wget https://paddle-qa.bj.bcebos.com/zhengtianyu/tools/llm-deploy-linux-amd64
+          wget --no-proxy https://paddle-qa.bj.bcebos.com/zhengtianyu/tools/llm-deploy-linux-amd64
           chmod +x ./llm-deploy-linux-amd64
           ./llm-deploy-linux-amd64 -python python3.10 \
           -model_name ERNIE-4.5-0.3B-Paddle \
@@ -279,3 +294,10 @@ jobs:
           fi
           echo "TEST_EXIT_CODE=${TEST_EXIT_CODE}"
           exit ${TEST_EXIT_CODE}
+
+      - name: Terminate and delete the container
+        if: always()
+        run: |
+          set +e
+          docker exec -t ${{ runner.name }} /bin/bash -c 'find /workspace -mindepth 1 -delete'
+          docker rm -f ${{ runner.name }}