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
- [WIP] fix
- [SPEC][SPEC V2][3/N] feat: adaptive spec support standalone(v1/v2)
- [Fix] add multiprocessing spawn as start method to avoid CUDA re-initialize…
- [Quant] Fix NVFP4 MoE input scale EP sharding in generic post-load path
- [bug fix] test/glm_51_fp8: cap max_running_requests on TP8+DP8 to fix B200 OOM
- docs(DeepSeek-V4): add DeepEP num_sms=96 to PD-Disagg Blackwell
- Extend Qwen3-VL EAGLE3 draft support
- killall.sh: sync sglang serve pattern with cli; strengthen deprecation
- [feat] Add Qwen3 MoE true-on-policy parity
- [vlm] declarative HF_KEY_RENAMES on the base mm processor
- Docs
- Python not yet supported