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
- fix(trace): extract context from incoming request headers
- fix decode_hicache send metadata bug
- CUDA coredump in FlashInfer `RadixTopKRenormProbKernel_MultiCTA`
- [Fix] Scope Gemma 4 image masks to sliding attention
- optimization sana-videa and ltx2
- [Feature] Add `--verify-attention-backend` for speculative target verify
- [Model] Fix BF16 MTP shared head loading for Step-3.7-Flash-NVFP4
- [Bugfix] Allow DSV4 FP4 dequant with triton; fail early on unsupported combo
- Kan/rust tm rust mm
- [Fix] Report which limit bound `max_running_requests`
- Docs
- Python not yet supported