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] glm4v: Align mRoPE with final input IDs
- [Fix] parser: Handle whitespace in force-nonempty fallback
- [Fix] ollama: Normalize chat inputs and bound default output tokens
- [Feat] wan2.2-s2v: Add a cache-dit block adapter
- [Feat] [Intel] fused_topk: Add 512 num_experts for fused_topk of xpu
- [Feat] wan2.2-s2v: Make the video API serve S2V
- [Test] [MUSA] sgl-kernel: Cover fused GEMV and MoE GEMV
- [Test] [NPU] speculative: Cover target-only acceptance thresholds
- [Fix] beam_search: Allow beam search with SWA hybrid caches
- [Feat] [NPU] multimodal: Add opt-in cross-request ViT image batching
- Docs
- Python not yet supported