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
- [AMD] Enable DSV4 unified-KV HiSparse PD over MoRI
- [DFLASH] Remove FlashInfer and MRoPE host syncs
- [Bugfix] Support arbitrary expert counts in no-copy-engine transfer
- Add a consecutive-prefill budget to bound decode starvation
- Support DCP and speculative decode in TRTLLM MHA
- [RFC] KVCR as a HiCacheStorage backend for peer-to-peer KV reuse
- support longcat-flash-lite-sparse
- feat(load-monitor): add Router-side engine load monitoring
- [Bug][kimi-k3] Long-context [PAD] (id 163839) storms + DSPARK inf/nan asserts — NaN-contaminated logits; released kimi-k3 image predates #32477; pad not stopped/filtered; allowed_special="all" makes [PAD] injectable
- [DeepSeek-V4] Support EAGLE3 for DeepSeek-V4-Flash-0731
- Docs
- Python not yet supported