Fast serving with structured output and prefix caching built into the runtime. Built by LMSYS.
Others in inference and serving
Common questions
Is SGLang free to use?
SGLang is open source and free to run yourself. You still pay whichever model provider you point it at, and this tutorial is free with no signup.
Do I need to know Python to use SGLang?
Basic Python is enough. Functions, dictionaries and imports cover most of what SGLang asks of you.
When should I not use SGLang?
When something else in inference and serving fits the job better. The others in that group are listed below.
Lessons for SGLang are being written. Meanwhile the APIs for AI tutorial covers the same ground: state, tools, loops, memory and human approval. Most of it carries straight over.
Start the APIs for AI tutorial →