Discover great AI tools
📢 NoticeWebsite launched:DeepToSeek AI tools directory is live. Submit great tools and get featured!
Home / Open Source Radar / Inference & Training / sglang

SGLang is a high-performance serving framework for large language models and multimodal models.

Stars39k
Forks10.6k
LanguagePython
LicenseApache-2.0
Last push2026-11-18

About this project

SGLang is a high-performance serving framework for large language models and multimodal models. It is infrastructure rather than a finished product: the layer that serves, quantises, trains or orchestrates models. It is maintained by sgl-project and published as a public repository you can read, fork and run yourself.

On GitHub the repository is tagged attention, blackwell, cuda, deepseek, diffusion, glm, gpt-oss, inference, llama and llm, which is a fair summary of what it covers. That generally means an API surface, batching and memory management, and often an OpenAI-compatible endpoint so existing clients keep working unchanged.

It is written mainly in Python and released under APACHE-2.0, a permissive license — commercial use is fine as long as copyright notices are kept. It is actively maintained: the most recent commit landed on November 18, 2026.

To try it, clone the repository and follow its README; that file is the canonical install guide. There is also a project page at https://sglang.io for documentation or a hosted demo. Because it runs on your own infrastructure, budget time for environment setup: dependencies, model weights and configuration usually take longer than the first successful run.

Key facts as recorded on GitHub: 39,005 stars; 10,586 forks; primary language Python; license APACHE-2.0; last commit on November 18, 2026; topics attention, blackwell, cuda, deepseek, diffusion, glm.