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
- [Doc] [NPU] deepseek-v4-flash: Document DSpark and Compact deployment
- [Spec] Fix trtllm_mha draft startup on GLM-5.3-Flash
- [Feat] [MLU] platform: Add initial support for Cambricon MLUs
- [Feat] kernels: Add Beam fused ops, router GEMMs and all-reduce boundary (3/7)
- [Feat] beam: Add Beam model, runtime support and checkpoints (4/7)
- [Perf] pd: Publish decode KV destinations without host syncs under overlap
- [Perf] deepseek-v4: Score a request's verify rows as one request in the C4 indexer
- [Feat] [NVIDIA] megakernels: Expose hybrid runtime views
- [CI] [Intel] disaggregation: Run XPU P/D nightly on Mooncake and NIXL
- [Fix] eplb: Load all local replicas of each expert
- Docs
- Python not yet supported