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(router): preserve upstream response headers
- [Temp][diffusion] model: Support MiniMax-H3 on Ascend A2/A3 Temporary Quick-Start Guide
- [Bug] DeepSeek-V4-Flash-0731 abnormal accuracy output when dp < tp
- [AMD] EAGLE3 spec-decode unsupported for MiniMax-M3: minimax_sparse_backend has no decode-shaped forward path (extend_seq_lens=None)
- [RFC] Distributed multimodal preprocessing for large multi-image requests in multi-node TP deployments
- OLMo-2 bypasses its own fused QK norm on every path except cuda-graph capture
- Fix hybrid-linear KV transfer under prefill pipeline parallelism
- [Bug] EXIF orientation is never applied when decoding images for VLM serving
- [Bug] DSPARK retrieves wrong key "acc_linear_penalities" from sampling_info
- Title: Inconsistent error response format with OpenAI standard for non-streaming requests
- Docs
- Python not yet supported