# Troubleshooting

**Model Deployment Issues**

If you encounter problems during model deployment:

1. Check the system logs:

   ```
   sudo journalctl -u soikastack -f
   ```
2. Verify GPU availability:

   ```
   nvidia-smi
   ```
3. Ensure you have sufficient disk space:

   ```
   df -h
   ```

**API Access Issues**

If you're having trouble with API access:

1. Verify your API key is active.
2. Check that you're using the correct endpoint URL.
3. Ensure your model is currently running.
4. Check for any IP restrictions on your API key.

### Best Practices <a href="#best-practices" id="best-practices"></a>

1. **Resource Management**: Stop models that aren't actively being used to free up GPU resources.
2. **Monitoring**: Regularly check the performance of your deployed models


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://soika-labs.gitbook.io/soika-mockingjay/soikastack-adding-llm-models-and-generating-api-keys/troubleshooting.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.