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
- [Feat][Multimodal] Add ViT patch-based admission control for multimodal requests
- fix: return 404 for unknown models on OpenAI-compatible endpoints
- fix: keep duplicate MCP namespace routing consistent
- [DSA] Add an arch-independent torch paged-MQA-logits backend with a fused Triton fast path
- [Proposal] Fuse static FP8 activation quantization into producer kernels (norm / activation / allreduce epilogue)
- [LoRA] Add /load_lora_adapter_from_distributed: load LoRA adapters via torch.distributed broadcast
- [LoRA] Support GDN in_proj_ba adapters for Qwen3.5
- support cp with tp
- Fix MiniMax sparse prefill score buffer OOB on stale max_seqlen_k
- [Bugfix] Reject incomplete trailing HiCache storage hits
- Docs
- Python not yet supported