zero-to-sglang is an open-source LLM inference tool published on GitHub by datawhalechina. It has 1.5k GitHub stars and 116 forks, and was last updated in October 2026. Docs and downloads are linked from datawhalechina.github.io.
“Official SGLang x Datawhale course on LLM inference: understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR. Available in English and Chinese.”
— datawhalechina, project description on GitHub
Details
| Category | Local LLMs & Inference |
|---|---|
| GitHub stars | 1,509 |
| Forks | 116 |
| Language | Python |
| Last updated | |
| Owner | datawhalechina |
| Website | datawhalechina.github.io/zero-to-sglang |
| Repository | datawhalechina/zero-to-sglang |
Tags
cudadatawhaleinference-engineinfrakv-cachellmllm-inferencesglang
Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.