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
- [sgl-kernel] Add SGLANG_KERNEL_DISABLE_FLASHINFER_NORM env var to force native norm ops
- [Feature] [Roadmap] Support Hygon HCU GPUs
- Fix(DSpark): Use Runtime Gamma In DSpark Confidence Head During CUDA Graph Capture
- fix(completion): treat None suffix as empty in FIM prompt builder
- docs: fix grammar and consistency in contribution guide
- perf(kernels/attention): parallelize compute_position prefix-sum for large batch
- [HiCache] Remove unused field `CacheInitParams::cache_ttl_second`
- fix(metrics): guard FPM decode metrics against None seq_lens_cpu
- fix(metrics): resolve router-included endpoint path for metrics
- fix(parser): Apertus2509Detector.force_nonempty_content silently no-ops on truncated streams
- Docs
- Python not yet supported