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
- [Bug] `--enable-memory-saver` crashes scheduler startup on CUDA 13 pip env: preload hook cannot resolve `libcudart.so.13`
- [Bug] `--enable-multi-layer-eagle` crashes on `LlamaForCausalLM` during startup
- Yan/glm53 router image
- [Bugfix] Abort streaming-session requests on client disconnect (#36475)
- [AMD] Support gfx942 in TileLang DSV4 indexer
- ROCm: charge the aiter paged-decode workspace against the KV pool instead of a flat mem-fraction haircut
- [LoRA] Add DeepSeek-V4 attention targets and disambiguate DSA wq_b
- [LoRA] Preserve DeepSeek-V4 grouped wo_a semantics
- [JIT Kernel] Migrate moe_sum from AOT to JIT
- [Bugfix] [OffloaderV1]Fix GemmaRMSNorm buffer handling
- Docs
- Python not yet supported