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
- fix(multimodal): restore SIGCHLD handler after process cleanup
- [mem_cache] SWA prefix lock pins one window, not a whole long ancestor
- [Bug] GLM-5.3-Flash-NVFP4 teacher-forced logprobs drift vs v0.5.20 on SM100 after 2026-09-18..09-21 (suspect #39688 KDA fusion gate)
- [XPU] upgrade sglang xpu backend to PyTorch 2.14
- [Bug][Simulator] --max-total-tokens on a hybrid mamba/GDN model crashes with TypeError: NoneType // int — the mamba sizing step is skipped on that branch
- [DSv4.1] Fold q_rope_store into fused_q_norm_rope
- [HiCache] Account for pending writes in file free-space watermark
- [Fix] Refresh attn_sink after loading weights
- [DSv4.1] Faster fp4 index-K gather and combine_topk_swa_indices
- [DSv4.1] Prefill indexer: raw selection, row-pair schedule ids, no host syncs
- Docs
- Python not yet supported