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
- [RL] Exempt non-weight buffers from the weight checker and compare MXFP4 Marlin experts dequantized
- [Kernel] cuDNN attention backend
- [Feature] Add examples for running SGLang on Slurm
- [Feature] Support more multi-modal input for VLM
- [Feature] Enable Two-Batch Overlap in Draft Models
- Kernel changes to support relaxed acceptance for thinking tokens in speculative decoding
- [Feature] Benchmark with audio input
- [FIX] Assert with hint if `page_size` is not `1` in Llama4
- feat(internvl): support internvl2_5 awq family
- Tiny add sanity check for torch empty tensors
- Docs
- Python not yet supported