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(quantization): reject K tiles that cross block-fp8 quantization blocks
- [diffusion] model: support HiDream-O1-Image
- [Performance] Cap SWA windows per radix path and reserve Mooncake loads
- fix(hicache): back up hybrid-Mamba prefixes whose last node ends exactly on a chunk boundary
- Preserve full DFlash draft KV during PD CPU retraction
- [Fix] Publish Mamba prefill cache updates before preparing the next batch
- Skip fully-masked KV tiles in sliding-window extend attention
- tokenizer perf optimization
- test(npu): add e2e test for --return-input-ids parameter
- test(npu): add e2e test for --return-output-ids parameter
- Docs
- Python not yet supported