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
- [Spec] Extract the shared forward step and introduce EagleWorkerContext
- [Fix] EP-slice ModelOpt NVFP4 input scales on the default MoE runner path
- fix(minimax-m3): stop streaming crash on non-finite number literal
- fix(minimax-m2): stop detect_and_parse crash on non-finite number literal
- [Fix] Handle BF16 and FP8 DeepEP dispatch in CUTLASS W4A8 MoE
- [Fix] Step3Detector drops tool-call parameters whose values contain '<'
- [AMD] fix: support both 4-arg and 6-arg vllm fused_add_rms_norm API
- [Feat] Add W4A16Sparse24 dense-dequant fallback for compressed-tensors int4
- [2/N] [spec] preserve verify capture mode on idle DP ranks
- Fix malformed Harmony output for gpt-oss + reasoning + json_schema (#31019)
- Docs
- Python not yet supported