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
- [CPU] enbale GLM_OCR
- [Kernel] Add out-of-tree dispatch for gated RMSNorm
- [XPU] Support Gemma-3 bidirectional image attention in XPUAttentionBackend
- [Fix] fix enable_deterministic_inference failed with enable_dp_attention
- Fix Description for MTP Model update_weights_from_tensor API OOM Issue
- Allow custom status codes to be returned for scheduler aborts.
- [AMD] Add kimi_linear_models test on AMD GPU
- [RFC] Sglang non-GPU process rust migration
- Fix ModelOpt NVFP4 MoE silently mis-serving parameterized-SwiGLU models
- fix dflash repetition penalties in spec-v2 target verification
- Docs
- Python not yet supported