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
- Feature/npu weight cache
- Feat/npu layernorm sp
- [AMD] Fix MiniMax-M3 EAGLE3 verification on ROCm
- [Fix] Respect shared-memory capacity in FP16 batch-invariant GEMM
- Test/npu hicache storage prefetch retry
- [diffusion] Enable SANA-Video 2.0 breakable CUDA graphs
- [Fix] /abort_request must not abort rids that share a prefix
- Test/npu speculative use rejection sampling
- [NPU]Update references from Ascend A5 to arch35 across multiple modules
- [Fix] targeted aborts matching unrelated request IDs
- Docs
- Python not yet supported