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
- [Bugfix] Wait for SGLang generation readiness in serving benchmark
- [Feature] support read/write datalake（iceberg、delta lake、paimon、lance）
- [Bugfix] Check paged KV capacity before kernel launch
- Add distributed exact input logprobs
- [AMD] Pin the exact ROCm Triton wheel instead of deferring to AITER
- [Constrained] Report the real cause when no grammar backend is available
- [VLM] Reuse Kimi-K3 embeddings before normal-serving preprocessing
- Unify the request length validation logic
- [Bugfix] Load official Gemma 4 unified config classes
- [Bug] Fix unreferenced fire-and-forget asyncio tasks
- Docs
- Python not yet supported