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
- [Benchmark] Add random shared-prefix dataset
- [cherrypick from #36389] [sglang][lora] Support DP attention in LoRA backends
- [Session] Wait for all DP session-open acknowledgments
- [WIP] prototype move runtime out of sgl-renderer
- [Fix] Abort over-length embedding requests before enqueuing
- docs: add thinking budget guide
- [DSV4.1] Add opt-in TRT-LLM sparse attention support
- [AMD] ci: build and nightly-test the miles ROCm 10 MI30X image
- [Bug] SM120: block-FP8 linears ignore scale_fmt "ue8m0" for activations (cutlass path uses FP32 amax/448 scales)
- [sgl-router] Exclude portless prefills and retry bootstrap discovery
- Docs
- Python not yet supported