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
- MLA decode-side KV broadcast: one rank pulls over the network, relays over NVLink
- feat(pd-flip): add runtime role switching and coordinated migration
- fix(attention): auto-split SM120 FA4 target verification
- [NPU] Remove stale SGLANG_ENABLE_SPEC_V2 usages
- Validate MoRI decode-mode dispatch token budget
- Coop indexer topk sm100
- fix: keep FlashInfer MLA graph kv_indptr current
- Fix tokenizer support
- fix(bailing): pass qualified prefix to lm_head
- [Spec] Gate plan-stream verify prep on the draft/tree handoff frontier (stacked on #36507)
- Docs
- Python not yet supported