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
- Store index cache per page independently and enable hicache offload for GLM-5.3-Flash
- [Speculative] Support Domino GRU on NPU via manual BF16 cell
- [CPU][kernel] fix rope for VLA model on CPU
- [NPU] support --enable-int8-mamba-checkpoint
- feat(npu): support startup-weight-load-mode=overlap on NPU
- [Fix] Align native generate logprob metadata with Python
- [Spec] QSA: let the pending index-K ring hold more than one compression group
- [AMD] Chunk MXFP8 block conversion to reduce load-time memory
- Let decode ranks contribute passive Mooncake store capacity
- [Bug] Spec-v2 workers diverge on forward_batch_generation signature — 4 of 7 missing pp_proxy_tensors the scheduler always passes
- Docs
- Python not yet supported