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
- DeepSeek-V4 shared_expert and ep normal using fused swiglu and quant
- Integrating LiteAttention Backend
- [kv-events] Surface cache salt on BlockStored.extra_keys
- [CPU][Compile] minor fix for compile fake tensor register with scheme
- [scheduler] Keep stop-the-world GC pauses off the batch critical path
- fix(spec): don't inherit target quantization for an unquantized EAGLE3/MTP draft
- [Unified Tree]Support host-only HiCache tree
- [router] Add decision-level observability to the cache-aware routing policy
- [DFlash] Support grammar constrained decoding support for DFlash
- [BugFix] Support DSA draft indexer restore in HiCache
- Docs
- Python not yet supported