This example shows how to use the `StreamGenerationTask` and `stream_generation_handler` to enable efficient streaming-based generation workflows.

How to run the example?

```bash
python stream_generation_run.py
```

See more detail on [tensorrt_llm/scaffolding/contrib/AsyncGeneration/README.md](https://github.com/NVIDIA/TensorRT-LLM/blob/main/examples/scaffolding/contrib/AsyncGeneration/README.md).