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
- [AMD] Refuse RCCL all-reduce in deterministic mode above TP2
- Include FlashInfer’s default tactic in startup tuning.
- [Roadmap] Prefill-Decode Disaggregation Roadmap (2026 Q4)
- [diffusion] comfyui: apply ControlNet residuals in Flux integrated mode
- [AMD] Bypass AITER GEMM and MoE in deterministic mode on gfx950
- [Fix] Preserve nullable string tool arguments
- [diffusion] fp8_fa_sm120: use the block-scaled MMA encoding
- fix: preserve Qwen3-VL sub-config objects
- Keep code fences in streamed DeepSeek-V3 answers when tools are set
- [Fix] Harmony parser: keep the response when a block opens on an unknown channel
- Docs
- Python not yet supported