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
- fix(server_args): gate trtllm_mla prefill (not decode) off SM120/SM121
- [function_call] Fix MiniMax-M2 single-shot tool_index ordinals
- Fix Qwen3.5 ModelOpt NVFP4 checkpoint loading
- [Roadmap] SGLang CI Pipeline Planning for NPU(2026 Q3)
- [Docs] Fix broken cross-page links in cookbook and Ascend NPU docs
- Fix aiter/wave cuda_graph_custom_mask undersize on long-context spec verify
- Redact secret fields from server_info responses
- fix: use system DP rank for prefill sender
- perf: use torch.empty for HiCache dummy read buffers to skip a memset
- Build SWA window kv buffers for the EAGLE draft-extend cuda-graph path
- Docs
- Python not yet supported