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
- [Model] support MiniMax-M3 DSpark inference
- [Bug] /v1/messages streaming thinking blocks can end without a signature
- [managers] Preserve trailing [SEP] when auto-truncating encoder embedding inputs
- [lora] Support LoRA for the NemotronH_Nano_VL_V2 model family
- Support consumer Blackwell (SM120/SM121) for NVFP4 serving - especially for rtx pro 6000
- [CI] Make /rerun-test honor disabled= registrations
- [Intel GPU] Upgrade PyTorch XPU version to 2.14
- [AMD] Resolving bug in per batch size graph capture due to multiple capture runs per batch size
- [DSV4.1][SM120] Tune block-FP8 decode for RTX PRO 6000
- [AMD][Qwen3-Next] Consume the AITER fused GDN prefill kernel
- Docs
- Python not yet supported