sglang
https://github.com/sgl-project/sglang
Python
SGLang is a high-performance serving framework for large language models and multimodal models.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported1 Subscribers
Add a CodeTriage badge to sglang
Help out
- Issues
- [Bug] `get_token_ids_logprobs` returns a plain `[]` instead of a tensor for absent entries, crashing decode logprob post-processing
- [Bug] HarmonyParser silently deletes streamed content that is a prefix of "commentary"
- [DSv4.1] Fold encoder-SWA replay into the extend forward
- [SWA] Keep a whole window behind the page an insert can end on
- [unified-memory] Stop allocation eviction on the joint FULL/SWA fit
- [unified-memory] Free SWA segments without a host sync
- [GDN] Auto-select FlashInfer prefill on a page-major pool
- [CP] Enable opt-in interleave prefill BCG for GLM-5.3 Flash
- [Bug] [diffusion] ComfyUI executor drops conditioning after rebuilding a dead worker mid-run
- [Bug] [diffusion] ComfyUI server-mode video nodes fail on current ComfyUI and need a local output file
- Docs
- Python not yet supported