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
- [Bugfix] Manually register kv_b_proj to attn_mha so mla model work with ShardedModelLoader
- [Bugfix] Accept Anthropic x-api-key authentication
- [Bug] 0.5.17: generation degenerates into token loops on Qwen3.5-arch model (works on 0.5.6.dev, with/without DFLASH)
- [multimodal] MiniMax-H3: accept target.width/height as an exact canvas
- [Feature] Support Prometheus name[] filtering for multiprocess metrics
- fix: FA4 paged-KV zero-size page-table registers on SM90
- [Router] Add abort_request fan-out support
- feat(kimi-k3): support DFLASH speculative decoding
- fix(speculative): reject zero-probability draft tokens
- RFC: Re-layer Draft SWA into Committed Sidecar KV and Verify Scratch
- Docs
- Python not yet supported