feat: add pingora-proxy-manager/

src/ollama/README.md

@@ -9,13 +9,13 @@ This service deploys Ollama for running local LLM models.
 - Pull DeepSeek R1 7B model:
 
   ```bash
-  docker exec -it ollama ollama pull deepseek-r1:7b
+  docker exec -it ollama-ollama-1 ollama pull deepseek-r1:7b
   ```
 
 - List all local models:
 
   ```bash
-  docker exec -it ollama ollama list
+  docker exec -it ollama-ollama-1 ollama list
   ```
 
 - Get all local models via API:
@@ -36,3 +36,25 @@ This service deploys Ollama for running local LLM models.
 ## Volumes
 
 - `ollama_models`: A volume for storing Ollama models.
+
+## Troubleshooting
+
+### GPU Becomes Unavailable After Long Run (Linux Docker)
+
+If Ollama initially works on the GPU in a Docker container, but then switches to running on CPU after some period of time with errors in the server log reporting GPU discovery failures, this can be resolved by disabling systemd cgroup management in Docker.
+
+Edit `/etc/docker/daemon.json` on the host and add `"exec-opts": ["native.cgroupdriver=cgroupfs"]` to the Docker configuration:
+
+```json
+{
+  "exec-opts": ["native.cgroupdriver=cgroupfs"]
+}
+```
+
+Then restart Docker:
+
+```bash
+sudo systemctl restart docker
+```
+
+For more details, see [Ollama Troubleshooting - Linux Docker](https://docs.ollama.com/troubleshooting#linux-docker).

src/ollama/README.zh.md

@@ -9,13 +9,13 @@
 - 拉取 DeepSeek R1 7B 模型：
 
   ```bash
-  docker exec -it ollama ollama pull deepseek-r1:7b
+  docker exec -it ollama-ollama-1 ollama pull deepseek-r1:7b
   ```
 
 - 列出本地所有模型：
 
   ```bash
-  docker exec -it ollama ollama list
+  docker exec -it ollama-ollama-1 ollama list
   ```
 
 - 通过 API 获取本地所有模型：
@@ -36,3 +36,25 @@
 ## 卷
 
 - `ollama_models`: 用于存储 Ollama 模型的卷。
+
+## 故障排除
+
+### 长时间运行后 GPU 离线（Linux Docker）
+
+如果 Ollama 在 Docker 容器中最初可以正常使用 GPU，但运行一段时间后切换到 CPU 运行，且服务器日志中报告 GPU 发现失败的错误，可以通过禁用 Docker 的 systemd cgroup 管理来解决此问题。
+
+编辑主机上的 `/etc/docker/daemon.json` 文件，添加 `"exec-opts": ["native.cgroupdriver=cgroupfs"]` 到 Docker 配置中：
+
+```json
+{
+  "exec-opts": ["native.cgroupdriver=cgroupfs"]
+}
+```
+
+然后重启 Docker：
+
+```bash
+sudo systemctl restart docker
+```
+
+更多详情请参阅 [Ollama 故障排除 - Linux Docker](https://docs.ollama.com/troubleshooting#linux-docker)。