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-return-routed-experts` returns all-zero routings on the triton-kernels / flashinfer top-k paths
- fix: abort parallel sampling requests by caller rid
- [Fix] Keep every image, video and audio of a request when n > 1
- [Bug] GLM-5.3-Flash: compressed-tensors ignore list names the forget gate self_attn.forget_gate.f_{a,b}_proj, so RedHatAI/GLM-5.3-Flash-NVFP4 fails at construction
- fix(quant): translate grouped names in AutoRound packed module settings
- [Bug] MultimemAllGatherer in LogitsProcessor crashes with SIGFPE on platforms without CUDA multicast (WSL2), even with symm-mem flags off
- Guard MultimemAllGatherer against platforms without CUDA multicast
- [Diffusion] FLUX 3 video VAE: fused QKV norm + RoPE, cached RoPE tables
- [Bug] Hybrid-SWA + radix cache: admission livelock when the SWA prefix lock pins a finished request's untrimmed last chunk
- [gRPC] Expose configured engine shutdown through native RPC
- Docs
- Python not yet supported