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
- [Bug] GraniteMoE can't load with --moe-runner-backend flashinfer_trtllm (routing_method_type is None)
- [Feat] [Intel] docker/xpu: Upgrade oneAPI to 2026.1.3 and sglang-kernel-xpu to 0.5.0
- [PD] Add opt-in cross-request Mooncake KV batching
- [Feat] [NPU] speculative: support NGRAM decoding for MHA and MLA
- [Test] [AMD] deterministic: Add a TP2 deterministic inference test on MI35x
- [External Linker]Support prefetch interfaces
- [AMD] Small MoE sort: support the EP expert mask (stacked on #42498)
- fix(openai): preserve zero cached tokens when reporting is enabled
- [MemCache] Reclaim orphan Full KV in hybrid unified cache
- [AMD][DSV4.1][CP] Support interleave prefill CP with breakable CUDA graphs on ROCm
- Docs
- Python not yet supported