> For clean Markdown content of this page, append .md to this URL. For the complete documentation index, see https://docs.nvidia.com/dynamo/llms.txt. For full content including API reference and SDK examples, see https://docs.nvidia.com/dynamo/llms-full.txt.

# Text-to-Text (LLM Diffusion)

Diffusion Language Models generate text through iterative refinement rather than autoregressive token-by-token generation. The model starts with masked tokens and progressively replaces them with predictions, refining low-confidence tokens each step. See the [Diffusion Overview](/dynamo/dev/diffusion/overview) for backend setup.

LLM diffusion is auto-detected: when `--dllm-algorithm` is set, the worker automatically uses `DiffusionWorkerHandler` without needing a separate flag. For more details on diffusion algorithms, see the [SGLang Diffusion Language Models documentation](https://github.com/sgl-project/sglang/blob/main/docs_new/docs/supported-models/diffusion_language_models.mdx).

## Launch

```bash
cd $DYNAMO_HOME/examples/backends/sglang
./launch/diffusion_llada.sh
```

See the [launch script](https://github.com/ai-dynamo/dynamo/tree/main/examples/backends/sglang/launch/diffusion_llada.sh) for configuration options.

## Generate Text

```bash
curl -X POST http://localhost:8001/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "inclusionAI/LLaDA2.0-mini-preview",
    "messages": [{"role": "user", "content": "Explain why Roger Federer is considered one of the greatest tennis players of all time"}],
    "temperature": 0.7,
    "max_tokens": 512
  }'
```

## See Also

- [Diffusion Overview](/dynamo/dev/diffusion/overview)
- [SGLang Examples](/dynamo/dev/recipes/cli-templates/sg-lang)
- [SGLang Diffusion LMs (upstream)](https://github.com/sgl-project/sglang/blob/main/docs_new/docs/supported-models/diffusion_language_models.mdx)