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
- [Bug] DSpark draft query width is incorrect on FA3/FA4 when `sample_from_anchor=False`
- [Perf] [NVIDIA] kimi-k3: Fused NVFP4 routing preparation and prepared FP4 routing at M <= 8
- [Fix] kda: Honor state and replay dtype
- [Fix] rust-server: Reject whitespace inside a stop_regex repeat count
- [RFC] [Feat] megakernel: Platform seams for out-of-tree megakernel plugins
- [Perf] [NPU] attention: Avoid CPU sequence length synchronization for Kimi K3
- [Chore] [XPU] deps: Pin sglang-kernel-xpu by version using uv
- [Feat] disaggregation: Add connex as a KV transfer backend
- [Fix] attention: Make FlashInfer prefill bit-exact on radix-cache hits
- [RFC] [Feat] disaggregation: PD bootstrap for a linear-attention state group spanning attention-DP groups
- Docs
- Python not yet supported