diff --git a/docker/llm/README_backup.md b/docker/llm/README_backup.md
index 2b8e73af..e65d634e 100644
--- a/docker/llm/README_backup.md
+++ b/docker/llm/README_backup.md
@@ -42,7 +42,6 @@ export CONTAINER_NAME=my_container
 export MODEL_PATH=/llm/models[change to your model path]
 
 docker run -itd \
-    --privileged \
     -p 12345:12345 \
     --cpuset-cpus="0-47" \
     --cpuset-mems="0" \
diff --git a/docker/llm/inference-cpp/README.md b/docker/llm/inference-cpp/README.md
index d5847a7a..13afd4b4 100644
--- a/docker/llm/inference-cpp/README.md
+++ b/docker/llm/inference-cpp/README.md
@@ -165,7 +165,6 @@ docker rm -f $CONTAINER_NAME
 docker run -itd \
             -v open-webui:/app/backend/data \
             -e PORT=8080 \
-            --privileged \
             --network=host \
             --name $CONTAINER_NAME \
             --restart always $DOCKER_IMAGE
diff --git a/docs/mddocs/DockerGuides/docker_cpp_xpu_quickstart.md b/docs/mddocs/DockerGuides/docker_cpp_xpu_quickstart.md
index d57ab55b..f02170b2 100644
--- a/docs/mddocs/DockerGuides/docker_cpp_xpu_quickstart.md
+++ b/docs/mddocs/DockerGuides/docker_cpp_xpu_quickstart.md
@@ -207,7 +207,6 @@ docker rm -f $CONTAINER_NAME
 docker run -itd \
             -v open-webui:/app/backend/data \
             -e PORT=8080 \
-            --privileged \
             --network=host \
             --name $CONTAINER_NAME \
             --restart always $DOCKER_IMAGE
diff --git a/docs/mddocs/DockerGuides/vllm_docker_quickstart.md b/docs/mddocs/DockerGuides/vllm_docker_quickstart.md
index 7ebc890a..dd05c68f 100644
--- a/docs/mddocs/DockerGuides/vllm_docker_quickstart.md
+++ b/docs/mddocs/DockerGuides/vllm_docker_quickstart.md
@@ -24,8 +24,8 @@ docker pull intelanalytics/ipex-llm-serving-xpu:latest
 export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-xpu:latest
 export CONTAINER_NAME=ipex-llm-serving-xpu-container
 sudo docker run -itd \
-        --privileged \
         --net=host \
+        --group-add video \
         --device=/dev/dri \
         -v /path/to/models:/llm/models \
         -e no_proxy=localhost,127.0.0.1 \
diff --git a/python/llm/dev/benchmark/ceval/README.md b/python/llm/dev/benchmark/ceval/README.md
index 11863da6..79dbe58e 100644
--- a/python/llm/dev/benchmark/ceval/README.md
+++ b/python/llm/dev/benchmark/ceval/README.md
@@ -55,8 +55,8 @@ python eval.py \
 2. **Start Docker Container**:
    ```bash
    docker run -td \
-         --privileged \
          --net=host \
+         --group-add video \
          --device=/dev/dri \
          --name=$CONTAINER_NAME \
          -v /home/intel/LLM:/llm/models/ \