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
- [HiCache] Reset decode ReplaySSM ring cursor on load-back Mamba slots
- [HiCache] Fence full prefill CUDA-graph replay behind pending load-back
- fix: route Thor SM110 FP8 and ModelOpt NVFP4 auto backends
- [HiCache][PD] Allow DSA index-K elision under HiCache and disaggregation
- [Tokenizer] Optionally omit consumed processor input_ids from tokenized multimodal requests
- 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
- Docs
- Python not yet supported