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(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
- [Fix] pd: Size decode Mamba spec-state scratch by running batch, not decode extra slots
- [AMD][DSV4][1/8] fp8 unified_kv decode/verify on FlyDSL v4 nm decode with a latency-model split plan
- [Feat] [XPU] support speculative decoding for GDN
- feat(diffusion): add optional TinyVAE image and video decoding
- [NPU] Add multimodal diffusion jobs to NPU coverage pipeline with case-level pytest node ids
- [Feat] [CPU] model: Support Muse and LFM2.5 models on CPU
- [KDA] Speed up the ReplaySSM fold with narrower tiles and input prefetch
- Docs
- Python not yet supported