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 FlashInfer fusion for hybrid EP and TP
- [Fix] Guard fused silu_and_mul quant kernels against invalid launch configs
- Add XPU topk_transform ut
- [models] Support --load-format dummy for KimiLinearForCausalLM
- Fix streaming tool calls losing arguments when completed in the final delta
- Fix decode-side release crashes and allow decode radix cache with speculative decoding
- [RFC] Add CI Infrastructure for the SGLang MLU Backend
- [Spec] Clamp Step3p5MTP multimodal pad sentinels in draft embedding
- Fix false SM120 sparse-prefill test failures for the expected dense fallback
- Fix AttributeError when AutoProcessor resolves to an image-only processor
- Docs
- Python not yet supported