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
- [Perf] [XPU] activation: Add native-BF16 GELU lookup
- [Perf] hicache: overlap MLA host reloads with forward-layer broadcasts
- [NPU] Ascend TP MoE optimizations
- [Feat] hicache: Integrate MLA host dedup with UnifiedRadixCache
- [Fix] [AMD] mhc: Enable AITER kernels on gfx942
- [Chore] release: Bump docs install version to 0.5.22
- [Feat] [NVIDIA] deepseek-v4: Add deployed V4.1 SM80/A100 adaptation and opt-in optimizations
- [Roadmap] Muse Spark Open Development & Optimization
- [AMD] Use aiter pa_prefill_sparse for unified-KV sparse prefill on gfx1250
- [Fix] disaggregation: Select the staging device in DCP packing threads
- Docs
- Python not yet supported