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
- DO NOT MERGE - CI sandbox for stateless scheduler b
- fix(lora): support Gemma 4 native LoRA adapters without v_proj weights
- fix(speculative): fix infinite loop with repetition_penalty in DFlash by adding missing token accumulation and scaling penalties
- Speed up FP8 per-token quant vec8 stores
- [Spec] Add a ctx axis to the adaptive spec _route (BS × ctx → slot)
- [Fix] Avoid cross-node JIT build races on shared NFS caches
- [DeepSeek-V4]support dspark c128 online compressor
- feat(hicache): support Ascend Mamba host transfers
- [NPU] Enable LLaDA2.2 block routing and graph-captured JTI on Ascend
- [RFC] Apple Silicon serving redesign: Torch-owned SRT path with an exported whole-model MLX region (roadmap)
- Docs
- Python not yet supported