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
- Improve total prefix cache tokens available when using hicache + write back
- [DFlash2] Keep the greedy selector walk in range for all-NaN score rows
- [Scheduler] Keep waiting requests' cached prefixes resident under cache-agnostic policies
- [AMD] [GLM5] Use Triton sparse attention for GLM-5.3 on gfx950
- feat(amd): add native GLM MXFP4 Triton Gluon MoE backend
- Fix XQA draft extend with FP8 KV cache in trtllm_mha
- [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)
- [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] Faster fp4 index-K gather and combine_topk_swa_indices
- [diffusion] Fuse Flux3 rowwise FP8 quantization with Triton
- Docs
- Python not yet supported