---
id: "b635"
language: "en"
library: "tools"
official_url: "https://docs.sglang.io/"
profile_updated_on: "2026-10-22"
---

# SGLang

Inference framework for language and multimodal models, with prefix caching and multi-device serving.

- Company / organization: LMSYS
- Category: Model development
- Official website: [https://docs.sglang.io/](https://docs.sglang.io/)
- Profile updated: 2026-10-22


## Overview

SGLang is an open-source inference framework hosted by LMSYS for language, vision-language and other models. Install a runtime, load weights and launch a server, then send generation, streaming or tool-calling requests from applications. RadixAttention and prefix caching reuse shared context, while multi-GPU parallelism scales serving. The repository also contains SGLang Diffusion for image and video generation. Check current model, hardware and API compatibility lists.

## Official sources and references

- [Official website](https://docs.sglang.io/)

## Reading & subscriptions

- [Interactive profile](../../../products/sglang--b635.html)
- [Read](../../../read/en/products/sglang--b635.html)
- [JSON](../../../read/en/products/sglang--b635.json)

Descriptions summarize public information; consult official websites for features, pricing and regional availability.