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
- [BACKEND] Add Cambricon MLU rotary embedding regression
- feat(amd): add native GLM MXFP4 Triton Gluon MoE backend
- [Diffusion] Keep generic warmup valid for step-floored models and stop reporting a failed warmup as warm
- [NPU] Transfer MTP draft pools in MLA kernel_ascend L2 IO
- Add Atlas Cloud backend
- [RL] Build GDN gated norms on the model's device and pass Nemotron-H's layer id to TopK
- [Fix] Share DSA k-pool radix pages at pooled-key group granularity
- [AFD] Add attention–FFN disaggregation with pipelining and CUDA Graph support
- [DSV4.1] Remove host syncs from the prefill forward
- [Feature] Attention–FFN disaggregation with pipelining and CUDA Graph support
- Docs
- Python not yet supported