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
- [SM120] Read FlashInfer 0.7's DSV4 decode dispatch through membership
- [DSv4.1] Run the candidate indexer on SM12x through the paged decode path
- Run Qwen3.8-27B on small GPUs via SSD weight streaming; tune GDN deco…
- [Bug] DeepSeekV31Detector streaming drops the arguments when a complete tool call arrives in one delta
- test(multiplex): add CPU unit tests for pdmux context and scheduling mixin
- test(elastic_ep): add CPU unit tests for scale state machine and helpers
- test(checkpoint_engine): add CPU unit tests for checkpoint splitting and worker extension
- fix(function_call): stream DeepSeek V3.1 arguments that share a delta with a call boundary
- [Fix] Count admitted request ranges in prefill tile budgets
- [Fix] Keep ignore-eos admission states sorted
- Docs
- Python not yet supported