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
- [GDN] Hoist GDN extend preparation across layers
- FEAT/paged LoRA memory pool with page-Level eviction
- [HiSparse] Add standalone Quest GPU kernel primitives (Part 3 of 4)
- [AMD]Fuse Q/K L2 normalization in Qwen3.5 GDN
- [AMD] [Spec] Enable stochastic tree verification on ROCm
- [speculative] Support DFlash speculative decoding under PD disaggregation
- [Feature] Add a fused CUTLASS MXFP4A8 MoE backend for SM90.
- [NPU][Quant] Fix ModelSlim W8A8 loading for Qwen3.8-27B-W8A8: resolve fused in_proj_qkvz scheme, quantize vision encoder, flatten 3-D inputs in NPU W8A8 kernels
- fix(qsa): support SM120/SM121 sparse decode paths
- [Feature] Add Aaronson-Gumbel text watermarking
- Docs
- Python not yet supported