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
- [Fix] Require control-plane auth on mesh HA management routes (fixes #45006)
- [Bug] [model-gateway] QueueProcessor leaks a rate-limit token when a queued client disconnects
- [Fix] model-gateway: Return rate-limit token when queued client disconnects
- [AMD] Optimize Muse FP4 MoE
- [AMD] Fuse Muse router and pooler
- [AMD] Fuse Muse QKV processing
- [AMD] Fuse Muse unpooler
- [AMD] Reuse Muse attention metadata
- [AMD] Tune DFlash attention tiles
- [AMD] Add Muse SWA split-KV
- Docs
- Python not yet supported