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 Mooncake Store crash with asymmetric MHA models and disable incompatible JIT write-back
- [RL] GLM 5.2: skip shared indexer weights from RL weight check
- Enable tensor descriptors in the Triton extend-attention kernel
- [LoRA] [WIP] Add experimental MoL route-decode KV reuse patch
- [HiCache] fix: MooncakeStore(standalone) check fails for DeepSeek-V4 logical anchor pool
- [DLLM] Add GFusion and EBSampling
- [minimax m3] npu adaptor
- [Feature] Reuse OpenAI preprocessing for tokenize endpoints
- Fix stale _attn_sink_local cache after RL weight updates
- fix(nvila): remap vision_tower.vision_model.* weights for flattened SiglipVisionModel
- Docs
- Python not yet supported