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
- [Anthropic] Default thinking off when the thinking field is absent
- [Model] Support RWKV-7 (Goose)
- [LoRA] Fix crash loading GDN in_proj_qkv/in_proj_z adapters for Qwen3.5
- fix: keep auto-derived SGLANG_GRPC_PORT in range for high --port
- fix(docker): install distro and missing runtime Python deps in the runtime image
- [Fix] Support mimo state_capturer routing replay
- Fall back to two-shot all-reduce in TorchSymmMemCommunicator when multicast is unavailable
- [Fix] Preserve missing Mooncake decode prefix metadata
- [RFC] RuntimeContext as the configuration API
- [KDA] Fuse o_proj + MLP AllReduce with the next RMSNorm via LayerCommunicator
- Docs
- Python not yet supported