> ## Documentation Index
> Fetch the complete documentation index at: https://docs.sglang.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> Robot action generation with SGLang Diffusion and Vision-Language-Action policies.

SGLang Diffusion supports action generation alongside image, video, and audio generation. Vision-Language-Action policies map camera observations, language instructions, and robot state into continuous action chunks using the same `multimodal_gen` runtime.

This section groups dedicated action-policy recipes separately from media recipes so robot deployments can document their own input schemas, policy endpoints, cache behavior, and control-loop performance targets. See the [action API](https://docs.sglang.io/docs/sglang-diffusion/api/openai_api.md#action-generation-sglang-extension) for shared endpoints and [Cosmos3](https://docs.sglang.io/cookbook/diffusion/Cosmos/Cosmos3.md) for world-model action generation.

## OpenPI

> [card] [Pi0.5](https://docs.sglang.io/cookbook/vla/OpenPI/Pi0.5.md)

## FLUX

> [card] [FLUX 3 Action](https://docs.sglang.io/cookbook/vla/FLUX/FLUX-3-Action.md)

## Runway

> [card] [Praxis-1](https://docs.sglang.io/cookbook/vla/Runway/Praxis-1.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.