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][NPU] GPT-OSS FIA sink attention uses incompatible prefill and eager decode paths
- [NPU] Preserve GPT-OSS attention sinks in FIA prefill and eager decode
- [DSV41] Engram precompute on GPU
- 0SM KV Cache Allgather for KV Cache Sharding
- [AMD][V4.1] Prefill context parallel, FP8 unified KV and PD (1P1D) for DeepSeek-V4.1 on MI355X
- [ModelOpt] Support explicit Qwen vision and MTP NVFP4 metadata
- [Feat] [AMD] deepseek-v4.1: Add full mono decode
- [Feature] --moe-replicate-tp: replicated MoE with prefill sequence parallelism (Qwen3.5 MoE)
- [AMD][DSV4][8/8] gfx950 ROCm images: pin aiter to 02575f1c3a
- [Feat] FlashInfer: Add NVFP4 W4A16 and SiTU support to MegaMoE
- Docs
- Python not yet supported