sgl-project / sgl-project.github.io

SGLang Documentation This is the documentation website for the SGLang project (https://github.com/sgl-project/sglang). We recommend new contributors start from writing documentation, which helps you quickly understand SGLang codebase. Most documentation files are located under the folder. Docs Workflow Install Dependency **Linux:** **macOS:** Update Documentation Update your Jupyter notebooks in the appropriate subdirectories under . If you add new files, remember to update (or relevant files) accordingly. • ** ** manually runs all configured checks, applying fixes if possible. If it fails the first time, re-run it to ensure lint errors are fully resolved. Make sure your code passes all checks **before** creating a Pull Request. Documentation Style Guidelines • For common functionalities, we prefer **Jupyter Notebooks** over Markdown so that all examples can be executed and validated by our docs CI pipeline. For complex features (e.g., distributed serving), Markdown is preferred. • Keep in mind the documentation execution time when writing interactive Jupyter notebooks. Each interactive notebook will be run and compiled against every commit to ensure they are runnable, so it is important to apply some tips to reduce the documentation compilation time: • Use small models (e.g., ) for most cases to reduce server launch time. • Reuse the launched server as much as possible to reduce server launch time. • Do not use absolute links (e.g., ). Always prefer relative links (e.g., ). • Follow the existing examples to learn how to launch a server, send a query and other common styles. Documentation Build, Deployment, and CI The SGLang documentation pipeline is based on **Sphinx** and supports rendering Jupyter notebooks ( ) into HTML/Markdown for web display. Detailed logits can be found in the Makefile. Notebook Execution ( ) The target is responsible for executing notebooks before rendering: • Finds all files under (excluding ) • Executes notebooks in parallel using GNU Parallel, with a relatively small • Wraps execution with to reduce flaky failures • Executes notebooks via • Records execution timing in This step ensures notebooks contain up-to-date outputs with each commit in the main branch before rendering. Web Rendering ( ) After compilation, Sphinx builds the website: • Reads Markdown, reStructuredText, and Jupyter notebooks • Renders them into HTML pages • Outputs the website into: This directory is the source for online documentation hosting. Markdown Export ( ) To support downstream consumers, we add a **new Makefile target**: This target: • Does **not modify** • Scans all files (excluding ) • Converts notebooks directly to Markdown using • Writes Markdown artifacts into the existing build directory: Example: CI Execution In our CI, the documentation pipeline first gets all the executed results and renders HTML and Markdown by: Then, the compiled results are forced pushed to sgl-project.io for rendering. In other words, sgl-project.io is push-only. All the changes of SGLang docs should be made directly in SGLang main repo, then push to the sgl-project.io.