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
- [ROCm] Use the AITER sparse-MLA kernel for DSA prefill and decode
- fix: preserve Inkling empty-content round trips
- [Fix] HiCache prefetch progress TP all_reduce deadlock
- Add native gRPC reflection
- perf(gemma4): replace dense image masks with spans
- [Fix] Streaming logprobs: do not 500 on chunks without logprob fields
- docs: add GLM-Image to Cache-DiT supported models
- feat(speculative): add EAGLE3 and DFlash support for Qwen3-Omni
- [Logging] Add per rank step index and step time (decode and prefill) to the logger
- fix: forward PD routing fields in Anthropic Messages requests
- Docs
- Python not yet supported