> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/curator/llms.txt.
> For full documentation content, see https://docs.nvidia.com/nemo/curator/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/curator/_mcp/server.

# nemo_curator.backends.xenna.executor

## Module Contents

### Classes

| Name                                                                   | Description                                      |
| ---------------------------------------------------------------------- | ------------------------------------------------ |
| [`XennaExecutor`](#nemo_curator-backends-xenna-executor-XennaExecutor) | Executor that runs pipelines using Cosmos-Xenna. |

### API

```python
class nemo_curator.backends.xenna.executor.XennaExecutor(
    config: dict[str, typing.Any] | None = None,
    ignore_head_node: bool = False
)
```

**Bases:** [BaseExecutor](/nemo-curator/nemo_curator/backends/base#nemo_curator-backends-base-BaseExecutor)

Executor that runs pipelines using Cosmos-Xenna.
This executor provides integration between the nemo-curator pipeline framework
and the Cosmos-Xenna execution engine for distributed processing.

```python
nemo_curator.backends.xenna.executor.XennaExecutor._get_pipeline_config(
    key: str
) -> typing.Any
```

Get configuration value with fallback to defaults.

```python
nemo_curator.backends.xenna.executor.XennaExecutor.execute(
    stages: list[nemo_curator.stages.base.ProcessingStage],
    initial_tasks: list[nemo_curator.tasks.Task] | None = None
) -> list[nemo_curator.tasks.Task]
```

Execute the pipeline using Cosmos-Xenna.

**Parameters:**

The stages to run

The initial tasks to run. Empty list of Task is used if not provided.

**Returns:** `list[Task]`

list\[Task]: List of output tasks from the pipeline