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
- [Bug] DeepSeek-V4.1 + SGLANG_DEFAULT_THINKING=1: thinking block leaks into content when the request carries no reasoning_effort
- [Roadmap][Feature] Cambricon MLU Backend Support
- [Perf] spec: Drop the draft_probs buffer from tree_speculative_sampling_target_only
- [Feat] observability: Add configurable request log retention
- [Feat] Valen: Add native decision-head serving
- [Feat] decisions: Serve StartLux-Decision checkpoints on /v1/systemone
- [Bug] Context length is silently derived from model config when --context-length is unset (can silently truncate long inputs)
- [Fix] model_config: Surface the derived context_length when --context-length is unset
- [Feat] cp: Add KV layout hooks and padded storage accounting
- [Fix] http_server: Make SageMaker /ping reflect server readiness
- Docs
- Python not yet supported