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
- [Test] diffusion: Avoid the tile-sharding rendezvous port race
- [Feat] radix-cache: Add --system-prompt fixed-prefix optimization for hybrid Mamba models
- [NPU] Support automatic HCCL sizing
- [Fix] moe: Eliminate cross-warp race in EP scatter indices
- [Feature][Spec][Ngram] Freeze external-corpus SAMs into a compact layout after finalize()
- [Perf] quantization: Add the bias in the cuBLASLt epilogue for per-tensor FP8 linears
- [Feat] PD/HiSparse: Support MTP for hybrid DSA models
- [Perf] qwen3: Fuse SiLU*mul with the NVFP4 quantization of down_proj in Qwen2MLP
- [Feat] [AMD] mori: Run MORI EPv2 dispatch/combine on AsyncLL kernels for TBO
- [Fix] metrics: Handle CPU monitor clock resets after restore
- Docs
- Python not yet supported