diff --git a/docs/get_started/installation/kunlunxin_xpu.md b/docs/get_started/installation/kunlunxin_xpu.md
index e425d5ad7..51067e893 100644
--- a/docs/get_started/installation/kunlunxin_xpu.md
+++ b/docs/get_started/installation/kunlunxin_xpu.md
@@ -127,7 +127,7 @@ Deploy an OpenAI API-compatible server using FastDeploy with the following comma
 
 #### Start service
 
-**The ERNIE-4.5-300B-A47B-Paddle model is to be deployed with a configuration of 32K WINT4 utilizing 8 XPU cards (Recommended)**
+**Deploy the ERNIE-4.5-300B-A47B-Paddle model with WINT4 precision and 32K context length on 8 XPUs(Recommended)**
 
 ```bash
 python -m fastdeploy.entrypoints.openai.api_server \
@@ -140,7 +140,7 @@ python -m fastdeploy.entrypoints.openai.api_server \
     --gpu-memory-utilization 0.9
 ```
 
-**The ERNIE-4.5-300B-A47B-Paddle model is to be deployed with a configuration of 128K WINT4 utilizing 8 XPU cards**
+**Deploy the ERNIE-4.5-300B-A47B-Paddle model with WINT4 precision and 128K context length on 8 XPUs**
 
 ```bash
 python -m fastdeploy.entrypoints.openai.api_server \
@@ -153,7 +153,7 @@ python -m fastdeploy.entrypoints.openai.api_server \
     --gpu-memory-utilization 0.9
 ```
 
-**The ERNIE-4.5-300B-A47B-Paddle model is to be deployed with a configuration of 32K WINT4 utilizing 4 XPU cards**
+**Deploy the ERNIE-4.5-300B-A47B-Paddle model with WINT4 precision and 32K context length on 4 XPUs**
 
 ```bash
 export XPU_VISIBLE_DEVICES="0,1,2,3"
diff --git a/docs/zh/get_started/installation/kunlunxin_xpu.md b/docs/zh/get_started/installation/kunlunxin_xpu.md
index 479077797..ed3148613 100644
--- a/docs/zh/get_started/installation/kunlunxin_xpu.md
+++ b/docs/zh/get_started/installation/kunlunxin_xpu.md
@@ -128,7 +128,7 @@ P800 支持 ```ERNIE-4.5-300B-A47B-Paddle``` 模型采用以下配置部署（
 
 #### 启动服务
 
-**ERNIE-4.5-300B-A47B-Paddle 模型采用 32K WINT4 8 卡配置部署（推荐）**
+**基于 WINT4 精度和 32K 上下文部署 ERNIE-4.5-300B-A47B-Paddle 模型到 8 卡 P800 服务器（推荐）**
 
 ```bash
 python -m fastdeploy.entrypoints.openai.api_server \
@@ -141,7 +141,7 @@ python -m fastdeploy.entrypoints.openai.api_server \
     --gpu-memory-utilization 0.9
 ```
 
-**ERNIE-4.5-300B-A47B-Paddle 模型采用 128K WINT4 8 卡配置部署**
+**基于 WINT4 精度和 128K 上下文部署 ERNIE-4.5-300B-A47B-Paddle 模型到 8 卡 P800 服务器**
 
 ```bash
 python -m fastdeploy.entrypoints.openai.api_server \
@@ -154,7 +154,7 @@ python -m fastdeploy.entrypoints.openai.api_server \
     --gpu-memory-utilization 0.9
 ```
 
-**ERNIE-4.5-300B-A47B-Paddle 模型采用 32K WINT4 4 卡配置部署**
+**基于 WINT4 精度和 32K 上下文部署 ERNIE-4.5-300B-A47B-Paddle 模型到 4 卡 P800 服务器**
 
 ```bash
 export XPU_VISIBLE_DEVICES="0,1,2,3"