update

doc/LOW_PRECISION_DEPLOYMENT.md

 # Low-Precision Deployment for Paddle Serving
-Intel CPU supports int8 and bfloat16 models, NVIDIA TensorRT supports int8 and bfload16 models.
+(English|[简体中文](./LOW_PRECISION_DEPLOYMENT_CN.md))
+
+Intel CPU supports int8 and bfloat16 models, NVIDIA TensorRT supports int8 and float16 models.
 
 ## Obtain the quantized model through PaddleSlim tool
 Train the low-precision models please refer to [PaddleSlim](https://paddleslim.readthedocs.io/zh_CN/latest/tutorials/quant/overview.html).

doc/LOW_PRECISION_DEPLOYMENT_CN.md

 # Paddle Serving低精度部署
+(简体中文|[English](./LOW_PRECISION_DEPLOYMENT.md))
+
 低精度部署, 在Intel CPU上支持int8、bfloat16模型，Nvidia TensorRT支持int8、float16模型。
 
 ## 通过PaddleSlim量化生成低精度模型