We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 1b3e69c commit 084fbb8Copy full SHA for 084fbb8
1 file changed
llm/docs/FastDeploy_usage_tutorial.md
@@ -47,7 +47,7 @@ FastDeploy 为 PaddleNLP 静态图模型提供了高效的部署方案,模型
47
```
48
cd /home/workspace/models_dir
49
50
-# 导出的模型目录结构格式如下所示,理论上无缝支持 PaddleNLP 导出静态图模型,无需修改模型目录结构
+# 导出的模型目录结构格式如下所示,理论上无缝支持 PaddleNLP 导出的静态图模型,无需修改模型目录结构
51
# /opt/output/Serving/models
52
# ├── config.json # 模型配置文件
53
# ├── xxxx.model # 词表模型文件
@@ -138,10 +138,12 @@ bash start_server.sh
138
139
140
# port为上面启动服务时候指定的HTTP_PORT
141
+ > 测试前请确保服务IP和端口正确
142
+
143
live接口: (服务是否能正常接收请求)
- http://{ip}:{HTTP_PORT}/v2/health/live
144
+ http://127.0.0.1:8110/v2/health/live
145
health接口:(模型是否准备好推理)
- http://{ip}:{HTTP_PORT}/v2/health/ready
146
+ http://127.0.0.1:8110/v2/health/ready
147
148
149
## 服务测试
0 commit comments