# Running Pipelines

After creating the pipeline configuration file, it is time to run it. COSAP comes with a pipeline runner currently supported by [Snakemake](https://snakemake.readthedocs.io/en/stable/). To create a COSAP PipelineRunner:

```python
from cosap import PipelineRunner

runner = PipelineRunner()
```

You can then run the pipeline with the previously created config:

```python
runner.run_pipeline(pipeline_config=pipeline_config)
```

## Setting up GPU-Accelerated Pipeline Runner

COSAP supports the NVIDIA Parabricks suite for GPU accelerated tasks in several steps. Parabricks must be set up beforehand manually. To do this please follow the instructions at [Parabricks Documentation](https://docs.nvidia.com/clara/parabricks/4.0.1/index.html).

After you set up Parabricks, you can activate it in the pipeline runner as follows:

```python
from cosap import PipelineRunner

runner = PipelineRunner(device="gpu")
```


---

# 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://docs.cosap.bio/fundamentals/using-cosap/running-pipelines.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.