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
- Honor GPU stride across scheduler and encoder launchers
- [Fix] Report HiCache storage clear failures accurately
- Fix batch-invariant kernels for Qwen3.8 Flash-Next
- Bound encoder health checks while waiting for dispatch
- [AMD] Enable mixed wave32/wave64 ROCm AOT kernels
- [AMD] Enable GPT-OSS MXFP4 with Triton kernels on ROCm
- fix(gemma4): initialize unified LM-head state
- [AMD] Default consumer RDNA to Triton attention
- [Fix] Return an error for uninitialized weight-send groups
- [Fix] Use the reduced draft head for a tied Qwen3.5 MTP with --speculative-token-map
- Docs
- Python not yet supported