Skip to content

S
Serving

PaddlePaddle / Serving
大约 2 年 前同步成功

通知 187
Star 833
Fork 253
S
Serving
提交 8f8e5069 编写于 作者: Z zhangjun
浏览文件
操作

fix doc

上级 1f99d5b3
显示空白变更内容
内联 并排
Showing with 4 addition and 4 deletion
doc/LOW_PRECISION_DEPLOYMENT.md
浏览文件 @ 8f8e5069
...@@ -17,7 +17,7 @@ python -m paddle_serving_client.convert --dirname ResNet50_quant ...@@ -17,7 +17,7 @@ python -m paddle_serving_client.convert --dirname ResNet50_quant
``` ```
Start RPC service, specify the GPU id and precision mode Start RPC service, specify the GPU id and precision mode
``` ```
python -m paddle_serving_server.serve --model serving_server --port 9393 --gpu_ids 0 --use_gpu --use_trt --precision int8 python -m paddle_serving_server.serve --model serving_server --port 9393 --gpu_ids 0 --use_trt --precision int8
``` ```
Request the serving service with Client Request the serving service with Client
``` ```
......
doc/LOW_PRECISION_DEPLOYMENT_CN.md
浏览文件 @ 8f8e5069
...@@ -16,7 +16,7 @@ python -m paddle_serving_client.convert --dirname ResNet50_quant ...@@ -16,7 +16,7 @@ python -m paddle_serving_client.convert --dirname ResNet50_quant
``` ```
启动rpc服务, 设定所选GPU id、部署模型精度 启动rpc服务, 设定所选GPU id、部署模型精度
``` ```
python -m paddle_serving_server.serve --model serving_server --port 9393 --gpu_ids 0 --use_gpu --use_trt --precision int8 python -m paddle_serving_server.serve --model serving_server --port 9393 --gpu_ids 0 --use_trt --precision int8
``` ```
使用client进行请求 使用client进行请求
``` ```
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或