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
- [Feature] Support offload and wake up of SGLang Diffusion
- [NPU][Feature] optimize lm_head tp size customizable
- [Feat] [Ngram spec] Add triton kernel for generating tree_mask
- [Bug] Preserve DeepSeek-V3.2 tool-call markers in reasoning parsing
- [bugfix][AMD] Fix PPMissingLayer AttributeError for deepseek v2/v3 in aiter_gfx95 code path
- [Feature][MPS] Better memory management for Apple Silicon Macs
- [AMD][Dockerfile] Multi-stage build for ROCm image to reduce size.
- [Kernel] Gluon-optimized deepep post-reorder for MoE
- [AMD] Add kimi-k2.5 eagle3 support with unified attention.
- account for mamba state pools in unified memory sizing
- Docs
- Python not yet supported