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
- Reintroduce compiling grammar on TP0
- Refactor and unify retry executor
- [DLLM] Optimize batching algorithm efficiency
- [Feature] Unified JIT / Precompilation Cache Directory
- Support OpenAI input_audio content type for base64 audio (#19235)
- Refine bench serving script
- [Perf] Optimize prefill attention kernel config for SM90+
- [Speculative Decoding] Add TLI (Token-Level Intersection) — lossless speculative decoding for heterogeneous vocabularies
- [api_server] Plumb runtime multimodal kwargs
- [HiSparse][ROCm] Use TileLang NSA backend policy on HIP
- Docs
- Python not yet supported