> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://fr.nvidia-localization.ferndocs.com/fr/nemo/rl/latest/nemo-rl-models-generation-vllm/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://fr.nvidia-localization.ferndocs.com/_mcp/server.

# nemo\_rl.models.generation.vllm

## Sous-modules

* **[`vllm_worker_async`](nemo-rl-models-generation-vllm-vllm-worker-async)**
* **[`vllm_backend`](nemo-rl-models-generation-vllm-vllm-backend)**
* **[`config`](nemo-rl-models-generation-vllm-config)**
* **[`vllm_generation`](nemo-rl-models-generation-vllm-vllm-generation)**
* **[`vllm_worker`](nemo-rl-models-generation-vllm-vllm-worker)**
* **[`utils`](nemo-rl-models-generation-vllm-utils)**

## Contenu du module

### Données

`__all__`

### API

```python
nemo_rl.models.generation.vllm.__all__
```

**Valeur**: `['VllmConfig', 'VllmGeneration', 'VllmGenerationWorker', 'VllmAsyncGenerationWorker']`