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
- docs(npu): add NPU profiler analysis skill (#1102)
- [NPU] keep Qwen3.6 hybrid SSM state stable across radix modes
- [docs] Slurm: fix multi-node example, add single-node and offline batch examples
- [Bug] Qwen3.8 DFlash2 TTFT regresses 3.1% from db2eb475 to 95f5ecd3 on RTX PRO 6000 Blackwell
- [Feature] Dynamic verification for DFlash2
- [Fix] Preserve YAML lists for single-value config args
- [Bugfix] Fix Dots hybrid DSA/SWA default backend
- [Fix] Skip quantized MoE compatibility check for dense models whose configs inherit MoE fields
- [Bug] /v1/responses and /v1/chat/completions return 400 when a function tool has "strict": null
- Fix inverted assertion message for enable_mixed_chunk with speculative decoding
- Docs
- Python not yet supported