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
- Enabling DWDP Support for Intel XPU
- [NVIDIA][MegaMoE] Fix the default spec decoding moe backend when the target model uses flashinfer megamoe
- fix(xpu): align TorchCodec with Torch 2.13
- [AMD] Fix Quark block-FP8 loading in DeepSeek loader
- fix(function_call): use call position as streaming tool_index in CohereCommand4Detector
- [CPU] enable Mistral series models
- [Bug][LoRA] Honor PEFT use_rslora when computing adapter scaling
- [Bug] Severe repetition and degenerate loops in reasoning/output when serving GLM-5.3 with DFLASH speculative decoding
- fix(quant): use pack_factor for legacy packed params in vocab embedding
- fix(quark): compare config lists element-wise instead of as sets
- Docs
- Python not yet supported