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
- Ref aware unified kv buffer
- Support serving FP8 MoE via Marlin W8A16
- [Fix] Exclude GDN in_proj_ba (a/b gate) from on-the-fly FP8 quantization
- Add Mooncake Store file-level weight connector for SGLang
- mhc: portable Triton hc_split_sinkhorn fallback for non-TileLang bac…
- [security] Sanitize profiler output_dir to prevent path traversal
- [Bug] Synchronous request preprocessing blocks the API event loop and delays health endpoints
- Use DeepGEMM deduplication API
- update
- fix(reasoning): guard continue_final_message against non-string assistant content
- Docs
- Python not yet supported