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
- [Refactor] Drop placement values nothing reads
- [Refactor] Drop model placement attributes and parameters nothing reads
- [Refactor] Keep only the TP and PP groups on the model runner
- [Refactor] Let FusedMoE's weight-loading helpers read the layer's MoE-TP rank
- [Refactor] Stop passing models' layers the placement they already read
- [Refactor] Add make_pp_layers so models stop handing their PP position down
- [Refactor] Enter draft TP scopes by attention ownership and drop ModelRunner.tp_group
- [Feature] Add --attn-dp-size and deprecate --enable-dp-attention
- [diffusion] Encode the MP4 while the VAE decodes (MiniMax-H3, Wan)
- [NPU] Add tracing disaggregation and tool call test cases
- Docs
- Python not yet supported