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
- [CI] Re-add diffusion norm_tanh fused kernel tests
- [DP attn] Fuse fill_(0) + memcpy_triton into a single kernel
- [Bug] Logprob mismatch between Prefill and Decode (Exactly at Index 96) when using FP8 KV Cache on H100
- [HiSparse] Support Unified tree & HiCache
- [refactor] Drop redundant no-op init_forward_metadata override in TorchNativeAttnBackend
- [Bug] Gemma-4 mm: single non-RGB image crashes vision tower and kills scheduler (mat1 256 vs 768)
- [3/N]Qwen3.5Opt: Fuse sigmoid-mul for attention output gate
- fix(sampling_params): make max_new_tokens as optional
- DeepSeek-V4 shared_expert and ep normal using fused swiglu and quant
- Integrating LiteAttention Backend
- Docs
- Python not yet supported