diff --git a/docker/china/maca.Dockerfile b/docker/china/maca.Dockerfile
index 91f60f9c..9801cbf0 100644
--- a/docker/china/maca.Dockerfile
+++ b/docker/china/maca.Dockerfile
@@ -2,7 +2,7 @@
 # Base image containing the vLLM inference environment, requiring amd64(x86-64) CPU + metax GPU.
 FROM cr.metax-tech.com/public-ai-release/maca/vllm:maca.ai3.1.0.7-torch2.6-py310-ubuntu22.04-amd64
 # Base image containing the LMDeploy inference environment, requiring amd64(x86-64) CPU + metax GPU.
-# FROM crpi-4crprmm5baj1v8iv.cn-hang
+# FROM crpi-vofi3w62lkohhxsp.cn-shanghai.personal.cr.aliyuncs.com/opendatalab-mineru/maca:maca.ai3.1.0.7-torch2.6-py310-ubuntu22.04-lmdeploy0.10.2-amd64
 
 # Install libgl for opencv support & Noto fonts for Chinese characters
 RUN apt-get update && \
diff --git a/docs/zh/usage/acceleration_cards/METAX.md b/docs/zh/usage/acceleration_cards/METAX.md
index 157e8554..a98f8521 100644
--- a/docs/zh/usage/acceleration_cards/METAX.md
+++ b/docs/zh/usage/acceleration_cards/METAX.md
@@ -9,6 +9,8 @@ docker: 28.1.1
 
 ## 2. 环境准备
 
+maca加速卡支持使用`vllm`或`lmdeploy`进行VLM模型推理加速。请根据实际需求选择安装和使用其中之一:
+
 ### 2.1 使用metax官方镜像作为基础镜像构建vllm环境镜像
 
 - 1. 从metax官方仓库拉取基础镜像