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
- [EPD][Perf] GPU image preprocessing for Kimi-K2.5 on the encoder server & default load vit weight
- [AMD] Enable MTP/spec decoding with HiSparse on DSV4 unified-KV (ROCm)
- [Feature] Support same-GPU data parallelism via --gpu-id-step 0
- [Feat][DeepSeek V4] Shared KV Cache for Prefill CP
- [ROCm] Enable MiniMax-M3 MXFP8 AITER MoE
- [Feature][NPU][Quantization] Adapt Qwen3.5 Dense Model with MXFP8/MXFP4 (W8A8/W4A8/W4A4) Quantization Schemes on A5 NPU.
- [feat] Support more precision (e.g., nvfp4) for IPC weight loading
- feat(gemma4): make multimodal loading opt-in
- [Feature] Kimi K3 Roadmap
- [NVIDIA] DeepSeek V4 Perf Tracking
- Docs
- Python not yet supported