Skip to content

Commit 3010c22

Browse files
authored
[Docs] Fix serving doc (#3440) (#3467)
* Fix bugs * Add bold text * Remove unused * Remove redundant
1 parent 8155fc6 commit 3010c22

File tree

2 files changed

+9
-9
lines changed

2 files changed

+9
-9
lines changed

docs/pipeline_deploy/serving.en.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -12,8 +12,8 @@ Demonstration of PaddleX pipeline serving:
1212

1313
To address different user needs, PaddleX offers multiple pipeline serving solutions:
1414

15-
- Basic serving: A simple and easy-to-use serving solution with low development costs.
16-
- High-stability serving: Built on [NVIDIA Triton Inference Server](https://developer.nvidia.com/triton-inference-server). Compared to basic serving, this solution offers higher stability and allows users to adjust configurations to optimize performance.
15+
- **Basic serving**: A simple and easy-to-use serving solution with low development costs.
16+
- **High-stability serving**: Built on [NVIDIA Triton Inference Server](https://developer.nvidia.com/triton-inference-server). Compared to basic serving, this solution offers higher stability and allows users to adjust configurations to optimize performance.
1717

1818
**It is recommended to first use the basic serving solution for quick verification**, and then evaluate whether to try more complex solutions based on actual needs.
1919

@@ -268,7 +268,7 @@ Select the pipeline you wish to deploy and click "获取" (acquire). Afterwards,
268268

269269
The PaddleX high-stability serving solution is built on NVIDIA Triton Inference Server, allowing users to modify the configuration files of Triton Inference Server.
270270

271-
In the `model_repo/{endpoint name}` directory of the high-stability serving SDK, you can find one or more `config*.pbtxt` files. If a `config_{device type}.pbtxt` file exists in the directory, please modify the configuration file corresponding to the desired device type. Otherwise, please modify `config.pbtxt`.
271+
In the `server/model_repo/{endpoint name}` directory of the high-stability serving SDK, you can find one or more `config*.pbtxt` files. If a `config_{device type}.pbtxt` file exists in the directory, please modify the configuration file corresponding to the desired device type. Otherwise, please modify `config.pbtxt`.
272272

273273
A common requirement is to adjust the number of execution instances for horizontal scaling. To achieve this, you need to modify the `instance_group` setting in the configuration file, using `count` to specify the number of instances placed on each device, `kind` to specify the device type, and `gpus` to specify the GPU IDs. An example is as follows:
274274

@@ -321,7 +321,7 @@ First, pull the Docker image as needed:
321321
docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/hps:paddlex3.0.0rc0-cpu
322322
```
323323
324-
With the image prepared, execute the following command to run the server:
324+
With the image prepared, navigate to the `server` directory and execute the following command to run the server:
325325
326326
```bash
327327
docker run \

docs/pipeline_deploy/serving.md

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -12,8 +12,8 @@ PaddleX 产线服务化部署示意图:
1212

1313
针对用户的不同需求,PaddleX 提供多种产线服务化部署方案:
1414

15-
- 基础服务化部署:简单易用的服务化部署方案,开发成本低。
16-
- 高稳定性服务化部署:基于 [NVIDIA Triton Inference Server](https://developer.nvidia.com/triton-inference-server) 打造。与基础服务化部署相比,该方案提供更高的稳定性,并允许用户调整配置以优化性能。
15+
- **基础服务化部署**:简单易用的服务化部署方案,开发成本低。
16+
- **高稳定性服务化部署**:基于 [NVIDIA Triton Inference Server](https://developer.nvidia.com/triton-inference-server) 打造。与基础服务化部署相比,该方案提供更高的稳定性,并允许用户调整配置以优化性能。
1717

1818
**建议首先使用基础服务化部署方案进行快速验证**,然后根据实际需要,评估是否尝试更复杂的方案。
1919

@@ -263,13 +263,13 @@ paddlex --serve --pipeline image_classification --use_hpip
263263

264264
<img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipeline_deploy/image-2.png">
265265

266-
**请注意**:每个序列号只能绑定到唯一的设备指纹,且只能绑定一次。这意味着用户如果使用不同的机器部署产线,则必须为每台机器准备单独的序列号。**高稳定性服务化部署完全免费。**PaddleX 的鉴权机制核心在于统计各产线的部署数量,并通过数据建模为团队提供产线效能分析,以便进行资源的优化配置和重点产线效率的提升。需要特别说明的是,鉴权过程只使用硬盘分区 UUID 等非敏感信息,PaddleX 也并不采集设备遥测数据等敏感数据,因此理论上**鉴权服务器无法获取到任何敏感信息**
266+
**请注意**:每个序列号只能绑定到唯一的设备指纹,且只能绑定一次。这意味着用户如果使用不同的机器部署产线,则必须为每台机器准备单独的序列号。**高稳定性服务化部署完全免费。** PaddleX 的鉴权机制核心在于统计各产线的部署数量,并通过数据建模为团队提供产线效能分析,以便进行资源的优化配置和重点产线效率的提升。需要特别说明的是,鉴权过程只使用硬盘分区 UUID 等非敏感信息,PaddleX 也并不采集设备遥测数据等敏感数据,因此理论上**鉴权服务器无法获取到任何敏感信息**
267267

268268
### 2.3 调整配置
269269

270270
PaddleX 高稳定性服务化部署方案基于 NVIDIA Triton Inference Server 打造,支持用户修改 Triton Inference Server 的配置文件。
271271

272-
在高稳定性服务化部署 SDK 的 `model_repo/{端点名称}` 目录中,可以找到一个或多个 `config*.pbtxt` 文件。如果目录中存在 `config_{设备类型}.pbtxt` 文件,请修改期望使用的设备类型对应的配置文件;否则,请修改 `config.pbtxt`
272+
在高稳定性服务化部署 SDK 的 `server/model_repo/{端点名称}` 目录中,可以找到一个或多个 `config*.pbtxt` 文件。如果目录中存在 `config_{设备类型}.pbtxt` 文件,请修改期望使用的设备类型对应的配置文件;否则,请修改 `config.pbtxt`
273273

274274
一个常见的需求是调整执行实例数量,以进行水平扩展。为了实现这一点,需要修改配置文件中的 `instance_group` 配置,使用 `count` 指定每一设备上放置的实例数量,使用 `kind` 指定设备类型,使用 `gpus` 指定 GPU 编号。示例如下:
275275

@@ -322,7 +322,7 @@ PaddleX 高稳定性服务化部署方案基于 NVIDIA Triton Inference Server
322322
docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/hps:paddlex3.0.0rc0-cpu
323323
```
324324
325-
准备好镜像后,执行如下命令运行服务器:
325+
准备好镜像后,切换到 `server` 目录,执行如下命令运行服务器:
326326
327327
```bash
328328
docker run \

0 commit comments

Comments
 (0)