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
- [Bug] qwen3.8-27b toolcall error
- test: cover invalid DeepSeek OCR ngram config
- [Perf] Memoize Req.tail_str to halve stop-string decode calls per step
- fix(sgl-model-gateway): parse prefilled Qwen3 reasoning
- [Bug] DSA top-k v2: tie-overflow selection is not exact — silently returns wrong top-k members (follow-up to #30512 / #30645)
- [Perf] wave_backend: drop dead per-layer D2H sync in forward_extend
- [Perf] Avoid full-logits all-gather for TP greedy sampling
- [AMD] Define gfx1250 QuickReduce stubs
- [Docs] Fix JIT kernel example paths
- fix: exclude NaN-producing autotune config for DSA Triton prefill on ROCm
- Docs
- Python not yet supported