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
- [Perf] [AMD] muse-spark: Prefill and decode optimization
- [Perf] [NVIDIA] fp8: enable SPLIT_K/SWAP_AB block-fp8 configs on sm_120
- [CI] diffusion: run MiniMax-H3-Image T2I and edit in the B200 suite
- [Test] [AMD] compat: Fix Python 3.10 test fixture cleanup
- [Fix] diffusion/zimage: Align request sizes to the 16-pixel patch grid
- [Refactor] mm: import MM_PAD_SHIFT_VALUE instead of re-declaring it
- [Fix] scheduler: Answer health probes that are waiting behind other requests
- [Fix] flexkv: Isolate FlexKV KV by the request's cache namespace
- [Perf] [AMD] rocm: Install fastokens in the ROCm image
- [Fix] function_call: Align DeepSeek DSML streaming with one-shot parsing
- Docs
- Python not yet supported