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
- [Refactor] diffusion: Remove dead code in configs and loaders
- [Refactor] diffusion: Remove dead code in models and pipeline stages
- [Refactor] diffusion: Remove dead test helpers, orphan perf baselines and unused CI code
- [Perf] Z-Image: Batch CFG branches in eager inference
- [Test] attention_unittest: Drop the duplicated draft-extend prefix-len helper
- [Fix] deepseek-v4: Pass expert offloader_kwargs so --offload-group-size works
- [Feat] kimi_k3: Support ModelOpt MXFP8 KDA for Kimi-K3.1-Pro
- [Perf] [AMD] quark: Pad W4A4 MXFP4 MoE to 128 columns for AITER FlyDSL
- [Fix] EPLB: Support pipeline-parallel GPU EPLB weight migration with …
- [Refactor] scheduler: Name the forward-on-its-own-stream condition once
- Docs
- Python not yet supported