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
- [Proposal] Memory-semantic PD-disaggregation paradigm
- Add continuous profiling in sgl-router
- fix: main block return hidden states before norm for MiMo v2 flash
- Fix qwen3 next kv cache scale name mismatch for ModelOpt NVFP4 checkpoint
- [Feature] Refactor common test entries of SGLang Diffusion
- [Gateway] Fix worker role corruption when K8s pod IP is reused across PD roles
- [AMD] Support context parallel for DeepSeek-V3.2 on AMD GPUs and add its test to nightly CI
- [Roadmap] Unified Hybrid Radix Cache Refactor
- [Bug] flashinfer gdn kernel not working
- [Enhance] log HTTP 400 validation details
- Docs
- Python not yet supported