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
- Fix http connections gauge leak
- FlashInfer Backend for MXFP8 Grouped Quantization
- [HiSparse][1/n] Add Dynamic HiSparse Residency to Preserve Small-Batch Decode Performance
- ci(deepep): purge stale deep_ep eggs before rebuild
- [sgl-kernel] Diagnose libtorch ABI mismatch on import instead of a cryptic undefined symbol
- [AMD] [GLM5] Fix MTP layer_quant_config in-place mutation + add nextn Quark-exclude unit test
- [AMD] GLM-5.1-FP8: MI300X benchmarks + FP8 cells
- Fix intermittent hybrid-decode EP deadlock under overlap scheduler
- [Bug] sgl-router (PD): open circuit breaker still dispatches to decode, producing a permanent fake-dead prefill
- benchmark: MI300X BF16 speed + accuracy data for Gemma 4 31B
- Docs
- Python not yet supported