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
- fix(bench_serving): always update output_len for sglang-oai completions
- [CPU] Part II: Add DeepSeek v4 support and optimizations on CPU
- [NVIDIA] Fix BF16 FlashInfer TRTLLM MoE RL weight update
- Fix strict-thinking vocab masks for llguidance / outlines backends
- fix: handle multi-token think_end_token without crashing
- Fix Gemma3 default RoPE parameter handling
- feat(tool-call): support per-token streaming for MiMo tool calls
- [DeepSeek-V4] feat: W4A8 MXFP4 MoE backend for DeepSeek-V4 on SM90 (FlashInfer)
- [NPU] add device print
- [metrics] Add cache eviction lifetime/frequency metrics (L1 + L2)
- Docs
- Python not yet supported