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
- Revert "ci: temporarily disable A5 (950) nightly job during power maintenance (#41856)"
- [Performance] Add adaptive KV-split cap for Triton GQA decode
- [Fix] Cap SWA lock-walk pinning at one window in the Rust TreeCore
- Use a separate workspace for fmha_v2 prefill in trtllm_mha
- [Diffusion] Fuse FLUX3 SwiGLU with rowwise FP8 quantization
- feat(kv-cache): generic OCP MXFP4 (block-32) KV cache via FlashMLA on SM100
- Avoid unsafe pickle fallback when loading PyTorch checkpoints
- [Bug] Qwen3CoderDetector: a string parameter whose value is `null` becomes null, and an invalid boolean becomes false
- [Bug] Glm47MoeDetector: a string parameter whose value is a quoted literal loses its quotes
- [Doc] cookbook: Add Jais 3 deployment recipes
- Docs
- Python not yet supported