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
- [NPU][Test] Add --fuseep-mode 1 testcase
- [Bug] GPTQ Marlin MoE fails or produces NaNs with BF16 and tensor parallelism
- Use `dtype` instead of deprecated `torch_dtype` for transformers >= 4.56
- fix: use dtype instead of deprecated torch_dtype
- docs(cookbook): add --enable-dp-lm-head to the Kimi-K3 GB200 decode cell
- [Fix][Humming] Initialize MXFP4 scales directly as E8M0
- [Bugfix] Route Qwen3 MoE through configured expert locations
- [GGUF] Fix qwen3_5 GGUF weight loading (conv1d / A_log / shared_expert_gate / lm_head qweight)
- [MiniMax-M3][AMD] Fix EAGLE3 TARGET_VERIFY on MI350/355 + AITER MXFP8 MoE
- fix(rocm): fall back to Triton when AITER does not support the GPU
- Docs
- Python not yet supported