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
- [NPU] add e2e test for --mamba-max-states-per-path eviction
- [New Model] Support Jina OCR
- [Feature] Support DSA PD with prefill CP and decode DCP
- Expose flush_cache timeout through the Python Engine API
- [Docs] Add tested Ascend A2 deployment and A3 reference for MiniMax-M2.5
- [mem_cache][Bugfix] Gracefully skip mamba cache donation on slot exha…
- [gRPC] Add standard health checks for Kubernetes probes
- fix: disable prefill cuda graph on low memory with quantized kv
- Store index cache per page independently and enable hicache offload for GLM-5.3-Flash
- [Speculative] Support Domino GRU on NPU via manual BF16 cell
- Docs
- Python not yet supported