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] Allow trtllm_mha for paged topk-1 speculation on SM100
- [ROCm][DSV4][BCG] Support bounded prefill context
- [Feature] Enable metadata glue graph for DFlash via host/device split
- [XPU] Add a release validation workflow for published Intel XPU images
- [DOC] Fix the typos in the document
- [NVIDIA][MegaMoE] Use persistent top-k reduce to eliminate decode latency overhead
- Cover SWA admission after declined HiCache restores
- [Bug] Python OpenAI Chat loses logprob candidates and streaming token records
- feat(hicache): opt-in exclusive L2->L3 tiering, dedup cache-mode L3 writes through the existence cache
- [Bug] [PD][NIXL] Receiver declares multi-component state transfer complete after first component
- Docs
- Python not yet supported