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
- [Feature] Unify the MoE router GEMM behind one gate layer
- [AMD] Optimize Qwen3.5 GDN prefill preparation and Triton recurrence on ROCm
- [Bug] GLM-5.3-Flash vision: single JPEG data URL is misidentified as an unrelated bird on 8x H20
- [XPU] Add XPU support to check_env.py
- [MoE] Coordinate NCCL EP Graph admission for zero-token ranks
- [Diffusion][SenseNova] Support the official 8-step distilled LoRA
- [Feature] Add --disable-normalize-embedding server arg
- [Bug] HiCacheFile reports an unrestorable prefix for hybrid cache pools
- support trace replay.
- [AMD] Add guarded gfx942 GLM shared-expert fusion opt-in
- Docs
- Python not yet supported