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] `--bf16-gemm-backend gemv` is accepted but unquantized linear layers never use it
- [XPU] Use the shared fused decode-metadata kernel in the intel_xpu ba…
- [PD] Slice appended hybrid draft KV across heterogeneous TP
- [rust-server] share model file and Hugging Face cache resolution
- [perf] [multi-lora] remove empty CTAs from fused LoRA expand and add split-K to shrink
- [Fix] Flush buffered text at stream end in MiniMax M2, MiniMax M3 and JsonArrayParser
- [NPU] [quantization] support NZ for w4a4 linear
- [AMD] Use AITER FP8 block selection for MiniMax-M3
- [Kimi K3] Strip a truncated think opening marker from parsed output
- [KDA] Support BF16 recurrent state in the CuTeDSL MTP verify kernel
- Docs
- Python not yet supported