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
- [DeepSeek V4.1] Support SM120 candidate fallback and extra KV pages
- [MLX] Fix the overlap-loop shutdown tests after unified request intake
- [AMD][DSV4] feat: enable PCP with fp8 unified_kv on gfx950
- [DO NOT MERGE][Personal review notes] DSV4 MemCache L3 code walkthrough
- [Fix] Return a tensor from the FlashKDA prefill fast path
- [Benchmark] Read HellaSwag from its HuggingFace mirror
- [Docs] GLM-5.3-Flash cookbook: warn about silent vision loss on pre-5.13 transformers builds
- [Rust] Fix commit-pinned tokenizer cache lookup
- Feature/npu sampling mask max tokens
- [Bug] Rust server cannot find a cached tokenizer when the model revision is a commit SHA
- Docs
- Python not yet supported