diff --git a/docker/llm/serving/xpu/docker/README.md b/docker/llm/serving/xpu/docker/README.md
index 23d6aff6..d4318025 100644
--- a/docker/llm/serving/xpu/docker/README.md
+++ b/docker/llm/serving/xpu/docker/README.md
@@ -26,7 +26,7 @@ To map the `XPU` into the container, you need to specify `--device=/dev/dri` whe
 
 ```bash
 #/bin/bash
-export DOCKER_IMAGE=intelanalytics/ipex-llm-xpu:2.2.0-SNAPSHOT
+export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-xpu:2.2.0-SNAPSHOT
 
 sudo docker run -itd \
         --net=host \
@@ -34,6 +34,7 @@ sudo docker run -itd \
         --memory="32G" \
         --name=CONTAINER_NAME \
         --shm-size="16g" \
+        --entrypoint /bin/bash \
         $DOCKER_IMAGE
 ```
 
@@ -71,7 +72,7 @@ By default, the container is configured to automatically start the service when
 
 ```bash
 #/bin/bash
-export DOCKER_IMAGE=intelanalytics/ipex-llm-xpu:2.2.0-SNAPSHOT
+export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-xpu:2.2.0-SNAPSHOT
 
 sudo docker run -itd \
         --net=host \
@@ -110,7 +111,7 @@ If you prefer to manually start the service or need to troubleshoot, you can ove
 
 ```bash
 #/bin/bash
-export DOCKER_IMAGE=intelanalytics/ipex-llm-xpu:2.2.0-SNAPSHOT
+export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-xpu:2.2.0-SNAPSHOT
 
 sudo docker run -itd \
         --net=host \
diff --git a/docs/mddocs/DockerGuides/docker_pytorch_inference_gpu.md b/docs/mddocs/DockerGuides/docker_pytorch_inference_gpu.md
index 1a692fce..a729f08f 100644
--- a/docs/mddocs/DockerGuides/docker_pytorch_inference_gpu.md
+++ b/docs/mddocs/DockerGuides/docker_pytorch_inference_gpu.md
@@ -32,6 +32,7 @@ Start ipex-llm-xpu Docker Container. Choose one of the following commands to sta
              --name=$CONTAINER_NAME \
              --shm-size="16g" \
              -v $MODEL_PATH:/llm/models \
+             --entrypoint /bin/bash \
              $DOCKER_IMAGE
   ```
 
@@ -52,6 +53,7 @@ Start ipex-llm-xpu Docker Container. Choose one of the following commands to sta
                   --shm-size="16g" \
                   -v $MODEL_PATH:/llm/llm-models \
                   -v /usr/lib/wsl:/usr/lib/wsl \ 
+                  --entrypoint /bin/bash \
                   $DOCKER_IMAGE
   ```
 
diff --git a/docs/mddocs/DockerGuides/docker_run_pytorch_inference_in_vscode.md b/docs/mddocs/DockerGuides/docker_run_pytorch_inference_in_vscode.md
index b6114ebd..46f3414f 100644
--- a/docs/mddocs/DockerGuides/docker_run_pytorch_inference_in_vscode.md
+++ b/docs/mddocs/DockerGuides/docker_run_pytorch_inference_in_vscode.md
@@ -66,6 +66,7 @@ Start ipex-llm-serving-xpu Docker Container. Choose one of the following command
              --name=$CONTAINER_NAME \
              --shm-size="16g" \
              -v $MODEL_PATH:/llm/models \
+             --entrypoint /bin/bash \
              $DOCKER_IMAGE
   ```
 
@@ -86,6 +87,7 @@ Start ipex-llm-serving-xpu Docker Container. Choose one of the following command
                   --shm-size="16g" \
                   -v $MODEL_PATH:/llm/llm-models \
                   -v /usr/lib/wsl:/usr/lib/wsl \ 
+                  --entrypoint /bin/bash \
                   $DOCKER_IMAGE
   ```
 
diff --git a/docs/mddocs/DockerGuides/fastchat_docker_quickstart.md b/docs/mddocs/DockerGuides/fastchat_docker_quickstart.md
index f2a684e9..5980e88b 100644
--- a/docs/mddocs/DockerGuides/fastchat_docker_quickstart.md
+++ b/docs/mddocs/DockerGuides/fastchat_docker_quickstart.md
@@ -29,6 +29,7 @@ sudo docker run -itd \
         --memory="32G" \
         --name=$CONTAINER_NAME \
         --shm-size="16g" \
+        --entrypoint /bin/bash \
         $DOCKER_IMAGE
 ```
 
diff --git a/docs/mddocs/DockerGuides/vllm_docker_quickstart.md b/docs/mddocs/DockerGuides/vllm_docker_quickstart.md
index 06025d93..d3c113fb 100644
--- a/docs/mddocs/DockerGuides/vllm_docker_quickstart.md
+++ b/docs/mddocs/DockerGuides/vllm_docker_quickstart.md
@@ -32,6 +32,7 @@ sudo docker run -itd \
         --memory="32G" \
         --name=$CONTAINER_NAME \
         --shm-size="16g" \
+        --entrypoint /bin/bash \
         $DOCKER_IMAGE
 ```
 
@@ -855,6 +856,7 @@ We can set up model serving using `IPEX-LLM` as backend using FastChat, the foll
             -e http_proxy=... \ 
             -e https_proxy=... \
             -e no_proxy="127.0.0.1,localhost" \
+            --entrypoint /bin/bash \
             $DOCKER_IMAGE
     ```
 
diff --git a/python/llm/dev/benchmark/ceval/README.md b/python/llm/dev/benchmark/ceval/README.md
index 79dbe58e..7f0a6327 100644
--- a/python/llm/dev/benchmark/ceval/README.md
+++ b/python/llm/dev/benchmark/ceval/README.md
@@ -64,6 +64,7 @@ python eval.py \
          -e http_proxy=$HTTP_PROXY \
          -e https_proxy=$HTTPS_PROXY \
          --shm-size="16g" \
+         --entrypoint /bin/bash \
          $DOCKER_IMAGE
    ```