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
- add EVEN_K heuristic for FP8GEMM efficient unmasked loads
- Reducing the time to import sglang
- [GDN/Qwen3-Next] Avoid SSM and conv state copy for speculative decoding - up to 9.47% e2e speedup
- Auto tuner support
- [WeightChecker][Fix] skip resetting buffers in WeightChecker
- [Rocm] add aiter fused qknorm + rope + set_kv + quant +shuffle
- A couple of fix for GLM models with special answer regex
- [fix ] fix vit torch compile and cuda graph incompatible problem
- [Bugfix] fix invalid non-printable character in `qwen2_classification.py`
- Fix: redact API secrets in ServerArgs repr and request header logs
- Docs
- Python not yet supported