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
- [Feature] Increase server payload size limit
- [Feature] Create benchmark and dataset usage scripts for embedding models
- [Performance] Remove instances of `torch.nonzero()` where appropriate
- [Feature] Integrate KVPress in order to try more KV cache optimization heuristics easily
- [BugFix] fix launching failed when `--enable-two-batch-overlap`
- Add bench serving video and tests
- [NPU] Fix Qwen3-AWQ npu_prefetch error
- [VLM] Refactor PaddleOCR to decouple with QwenVL
- for PP > 1, the last PP rank merges (to make sure all files exist)
- [Roadmap] Prefill-Decode Disaggregation Roadmap (2026 Q2)
- Docs
- Python not yet supported