> This page is for NeMo Fabric, version v0.1.0.
> For other versions, use one of these documentation indexes:
> - Latest (v0.4.0) (default): https://docs.nvidia.com/nemo/fabric/latest/llms.txt
> - dev: https://docs.nvidia.com/nemo/fabric/dev/llms.txt
> - v0.5.0: https://docs.nvidia.com/nemo/fabric/v0.5.0/llms.txt
> - v0.4.0: https://docs.nvidia.com/nemo/fabric/v0.4.0/llms.txt
> - v0.3.0: https://docs.nvidia.com/nemo/fabric/v0.3.0/llms.txt
> - v0.2.0: https://docs.nvidia.com/nemo/fabric/v0.2.0/llms.txt
> - v0.1.1: https://docs.nvidia.com/nemo/fabric/v0.1.1/llms.txt
> - v0.1.0: https://docs.nvidia.com/nemo/fabric/v0.1.0/llms.txt

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

# Streaming

> Consume raw NVIDIA NeMo Relay ATOF records and terminal invocation results.

# <kbd>module</kbd> `nemo_fabric.streaming`

NeMo Relay streaming support for the NVIDIA NeMo Fabric Python SDK.



---


## <kbd>class</kbd> `InvokeStream`

Async iterator of raw ATOF records for one runtime invocation.

Consume the final normalized result separately with :meth:`result`. If iteration stops early, call :meth:`aclose` before starting another turn.




---


### <kbd>method</kbd> `aclose`

```python
async def aclose() -> None
```

Stop iteration and drain this turn without cancelling the invocation.

---


### <kbd>method</kbd> `result`

```python
async def result() -> RunResult
```

Return the terminal normalized result without adding it to the stream.




---

_This file was automatically generated via [lazydocs](https://github.com/ml-tooling/lazydocs)._