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
- [Perf] [XPU] mamba: Fuse the Mamba-1 prefill selective scan into one Triton kernel
- [Fix] lora: Support Qwen3.5 GDN packed projections
- [Feat] [AMD] dsv4: FP4 indexer with natural layout and OPUS MQA logits
- [Fix] hicache: Register the whole host-pool allocation with Mooncake
- [Fix] kimi-k3: Reuse the attention-residual bank across forward passes
- [Perf] diffusion: Share convrot_int8 input quantization across LTX-2 projections
- [Feat] [AMD] diffusion: Add MXFP6 and A6W4 online GEMM quantization
- [Fix] anthropic: don't reject adaptive thinking when there is no reasoning parser
- [Fix] kimi-k3: Route DFLASH target verification to cutedsl_mla under DCP
- [Fix] openai: Avoid duplicate BOS on text-only requests to multimodal models
- Docs
- Python not yet supported