"...text-generation-inference.git" did not exist on "57b34958235ee64b7c310a4b5410bcc491a0ef28"
Commit 6eb54a55 authored by myhloli's avatar myhloli
Browse files

fix: add horizontal rules for better section separation in docker_deployment.md

parent 3f616ec6
...@@ -2,7 +2,7 @@ ...@@ -2,7 +2,7 @@
MinerU provides a convenient Docker deployment method, which helps quickly set up the environment and solve some tricky environment compatibility issues. MinerU provides a convenient Docker deployment method, which helps quickly set up the environment and solve some tricky environment compatibility issues.
## Build Docker Image using Dockerfile: ## Build Docker Image using Dockerfile
```bash ```bash
wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/global/Dockerfile wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/global/Dockerfile
...@@ -61,6 +61,8 @@ wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/compose.yaml ...@@ -61,6 +61,8 @@ wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/compose.yaml
>- Different services might have additional parameter configurations, which you can view and edit in the `compose.yaml` file. >- Different services might have additional parameter configurations, which you can view and edit in the `compose.yaml` file.
>- Due to the pre-allocation of GPU memory by the `sglang` inference acceleration framework, you may not be able to run multiple `sglang` services simultaneously on the same machine. Therefore, ensure that other services that might use GPU memory have been stopped before starting the `vlm-sglang-server` service or using the `vlm-sglang-engine` backend. >- Due to the pre-allocation of GPU memory by the `sglang` inference acceleration framework, you may not be able to run multiple `sglang` services simultaneously on the same machine. Therefore, ensure that other services that might use GPU memory have been stopped before starting the `vlm-sglang-server` service or using the `vlm-sglang-engine` backend.
---
### Start sglang-server service ### Start sglang-server service
connect to `sglang-server` via `vlm-sglang-client` backend connect to `sglang-server` via `vlm-sglang-client` backend
```bash ```bash
...@@ -72,6 +74,8 @@ connect to `sglang-server` via `vlm-sglang-client` backend ...@@ -72,6 +74,8 @@ connect to `sglang-server` via `vlm-sglang-client` backend
> mineru -p <input_path> -o <output_path> -b vlm-sglang-client -u http://<server_ip>:30000 > mineru -p <input_path> -o <output_path> -b vlm-sglang-client -u http://<server_ip>:30000
> ``` > ```
---
### Start Web API service ### Start Web API service
```bash ```bash
docker compose -f compose.yaml --profile mineru-api up -d docker compose -f compose.yaml --profile mineru-api up -d
...@@ -79,6 +83,8 @@ connect to `sglang-server` via `vlm-sglang-client` backend ...@@ -79,6 +83,8 @@ connect to `sglang-server` via `vlm-sglang-client` backend
>[!TIP] >[!TIP]
>Access `http://<server_ip>:8000/docs` in your browser to view the API documentation. >Access `http://<server_ip>:8000/docs` in your browser to view the API documentation.
---
### Start Gradio WebUI service ### Start Gradio WebUI service
```bash ```bash
docker compose -f compose.yaml --profile mineru-gradio up -d docker compose -f compose.yaml --profile mineru-gradio up -d
......
...@@ -2,7 +2,7 @@ ...@@ -2,7 +2,7 @@
MinerU提供了便捷的docker部署方式,这有助于快速搭建环境并解决一些棘手的环境兼容问题。 MinerU提供了便捷的docker部署方式,这有助于快速搭建环境并解决一些棘手的环境兼容问题。
## 使用 Dockerfile 构建镜像 ## 使用 Dockerfile 构建镜像
```bash ```bash
wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/china/Dockerfile wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/china/Dockerfile
...@@ -59,6 +59,8 @@ wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/compose.yaml ...@@ -59,6 +59,8 @@ wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/compose.yaml
>- 不同的服务可能会有额外的参数配置,您可以在`compose.yaml`文件中查看并编辑。 >- 不同的服务可能会有额外的参数配置,您可以在`compose.yaml`文件中查看并编辑。
>- 由于`sglang`推理加速框架预分配显存的特性,您可能无法在同一台机器上同时运行多个`sglang`服务,因此请确保在启动`vlm-sglang-server`服务或使用`vlm-sglang-engine`后端时,其他可能使用显存的服务已停止。 >- 由于`sglang`推理加速框架预分配显存的特性,您可能无法在同一台机器上同时运行多个`sglang`服务,因此请确保在启动`vlm-sglang-server`服务或使用`vlm-sglang-engine`后端时,其他可能使用显存的服务已停止。
---
### 启动 sglang-server 服务 ### 启动 sglang-server 服务
并通过`vlm-sglang-client`后端连接`sglang-server` 并通过`vlm-sglang-client`后端连接`sglang-server`
```bash ```bash
...@@ -70,6 +72,8 @@ wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/compose.yaml ...@@ -70,6 +72,8 @@ wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/compose.yaml
> mineru -p <input_path> -o <output_path> -b vlm-sglang-client -u http://<server_ip>:30000 > mineru -p <input_path> -o <output_path> -b vlm-sglang-client -u http://<server_ip>:30000
> ``` > ```
---
### 启动 Web API 服务 ### 启动 Web API 服务
```bash ```bash
docker compose -f compose.yaml --profile mineru-api up -d docker compose -f compose.yaml --profile mineru-api up -d
...@@ -77,6 +81,8 @@ wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/compose.yaml ...@@ -77,6 +81,8 @@ wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/compose.yaml
>[!TIP] >[!TIP]
>在浏览器中访问 `http://<server_ip>:8000/docs` 查看API文档。 >在浏览器中访问 `http://<server_ip>:8000/docs` 查看API文档。
---
### 启动 Gradio WebUI 服务 ### 启动 Gradio WebUI 服务
```bash ```bash
docker compose -f compose.yaml --profile mineru-gradio up -d docker compose -f compose.yaml --profile mineru-gradio up -d
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment