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
- [CI] [AMD] deepseek-r1: Align the MI35x MXFP4 TP4 MTP GSM8K gate with the non-MTP test
- [Fix] hf_transformers: Repair v5 tokenizer components on processor-loaded tokenizers
- [Perf] [AMD] quark: Compile each layer_quant_config pattern once
- [Fix] ModelOpt: Refuse layers whose quant_algo SGLang cannot build
- [Bug] EAGLE/EAGLE3 verify applies repetition_penalty to only one token per step, so speculative output differs from non-speculative decoding
- [AMD][K3.1] Balance the DSA indexer over long rows under DCP
- [Feat] RL: [sglang-miles] Re-land storing output store replay fields as layer blocks at layer splits (#48123)
- [Perf] multi-item-scoring: avoid host syncs in label-logprob readback and embed overrides
- [Fix] openai: handle string-keyed id2label and boolean inputs in OpenAIServingClassify
- [NPU] Verify DSPARK drafts in mixed chunk prefill
- Docs
- Python not yet supported