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
- [PoC] Optimize GPT-OSS CP4+EP4 prefill with breakable graphs and single-call zigzag attention
- perf(hicache): proactively finalize completed prefetch at scheduler safe point
- [Router] Add KV event gap replay for sgl-router
- [Bug] sgl-router decode affinity metric is never recorded
- [AMD] DO NOT MERGE - Test pr32754
- [Feature] Enable DeepSeek V4 IndexCache with PD, CP, and HiCache coverage
- [MLX] Guard GDNAttnBackend init when the mamba cache is not allocated
- [MLX] Fix device mismatch in forward token relay (enables batched decode)
- docs: recommend sglang serve in quickstart
- Fix three exception messages split across positional arguments
- Docs
- Python not yet supported