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
- Validate CuTe DSL online NVFP4 W4A16 configuration
- [Intel GPU] Use the fused bf16 x bf16 -> fp32 GEMM on XPU
- [Feature] MXFP4 KV Cache for Qwen3.5/3.8 (MHA) on SM120
- [Kernel] Add out-of-tree dispatch for causal Conv1D
- [Diffusion] Add Cache-DiT support for SenseNova-U1
- [Unified Memory] fix lazy Mamba buffer lifecycle
- [MoE] Support serial shared experts for NCCL EP Triton
- [Diffusion][SenseNova] Add SenseNova U1 image editing support
- [DCP] Restore GLM-5.3 Flash decode CP and fix virtual KV addressing
- fix(unified-memory): bound joint reclaim and preserve cached prefixes
- Docs
- Python not yet supported