sglang

sglang is an image-generation tool - SGLang is a high-performance serving framework for large language models and multimodal models.

Overview

SGLang is an open-source inference framework for large language, vision-language, and diffusion models, optimized for agentic workloads, large-scale serving, and RL rollouts. SGLang Diffusion is its built-in image and video generation engine, included in this repository and the 'sglang' Python package.

👋 Get started below, or meet the community at SGLang Events, including meetups, developer meetings, workshops, and office hours.

• Quickstart: Run your first model and send a request. - Cookbook: Choose your model and hardware to get a ready-to-run launch command.

SGLang supports a wide range of GPUs, TPUs, NPUs, CPUs, and Apple Silicon platforms.

Integrations in progress: AWS Trainium, Alibaba T-Head PPU, Cambricon MLU, Qualcomm QAIC, MetaX, Hygon HCU/DCU, Iluvatar CoreX, and more.

See the Cookbook and platform guides for model compatibility and setup.

Contributions are welcome, from bug fixes and documentation to model support and performance improvements.

Start from the 'lmsysorg/sglang:dev' Docker image, which provides development tools and most dependencies. Clone or mount your SGLang checkout inside the container, then install it in editable mode from the repository root so tests use your local Python changes:

In an activated virtual environment, you can use 'uv pip install --prerelease=allow -e "python"' instead. See the development guide for container setup and testing.

sglang is open-source, written primarily in Python, with 37,010 GitHub stars under the Apache 2.0 license. The latest release is v0.5.21 (2026-10-02).

Key capabilities

From the project's documentation:

• Quickstart: Run your first model and send a request.
• Cookbook: Choose your model and hardware to get a ready-to-run launch command.
• Community discussions: Join Slack for technical questions and development discussions.
• Events: Find meetups, workshops, and office hours on SGLang Events.

Install

A quick way to get started (always check the official docs for the latest):

pip install --prerelease=allow sglang

How it fits a local-AI stack

sglang runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related image-generation tools in the directory:

• Stable Diffusion WebUI (AUTOMATIC1111)
• ComfyUI
• "dynamo"
• Fooocus

Sources

• Source code & docs: sgl-project/sglang
• Official website: https://sglang.io

Stats from GitHub, 2026-10-12.