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
- [FlashInfer] Persist autotune results in the autotune_v2 managed store
- [ROCm] Tune FP8 query preparation for full-graph verification
- [Docs] Mark validated GLM-5.2 MI355X MXFP4 recipes
- [Bugfix][Responses API] Merge replayed assistant turn items when only some carry a phase
- Fix assistant phase grouping in Responses history
- fix(bf16-gemm): route gemv backend through UnquantizedLinearMethod.apply
- [Perf] Pack the Qwen3.5 GDN input projection on CUDA, including from the dense wrapper
- fix(multimodal): convert grayscale tensors to RGB in PIL backend
- [Bugfix] Fix per-request disallowed token masking
- [Bug] DeepSeekV31Detector.structure_info() omits `<｜tool▁calls▁begin｜>`, so its own detect_and_parse returns no tool call
- Docs
- Python not yet supported