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
- [MLX] Retracted request's decode KV can flush into a reused req_to_token row on the next extend forward
- [rfork] Fix client instances not registering weight_info to EngineInfoBootstrapServer
- [Bug] backend ignores bidirectional sliding window attention for encoder models
- feat: Add DeepEP custom wheel build workflow (#32607)
- [UT][NPU] Add unit tests for utils, CMO, memory pool, and allocator
- fix(responses): support Codex tool outputs and max effort streams
- [NPU] Adapt the Mellum2-12B-A2.5B-Thinking model on Ascend NPU
- Fix TopK output contracts under torch.compile
- [Model] Add K-EXAONE-2.0-750B-A37B support
- [perf] simplify text-only mrope positions calculation
- Docs
- Python not yet supported