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
- [Benchmark] Fix prompt token accounting and harden OpenAI dataset loading
- fix(metrics): report kv_*_blocks in pages, not tokens
- [BugFix] dspark for Qwen3.6 GDN recurrent state commit
- Defer gfx950 A8W8 quantization to AITER
- Fix constrained grammar stop-token handling
- FIX:copy-to-gpu-no-ce-arbitrary-n
- [AMD] Enable AITER CK bpreshuffle w8a8 block GEMM on gfx942 (MI300X), opt-in
- [Model] Support ZAYA1 native transformers checkpoint format
- [MoE] [minimax-m3] Add a memory-efficient contiguous DeepGEMM path for pure TP
- [easy][Cleanup] Drop unused tbo_split_seq_index in TBO replay_prepare
- Docs
- Python not yet supported