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
- [MLX] Honor checkpoint revision in one-batch benchmarks
- [Bugfix] Preserve Pythonic sibling calls with unsupported dictionary keys
- [Test] Frame the empty benchmark flush HTTP response explicitly
- [MLX] Expand home-relative Chrome trace export paths
- [AMD][DeepSeek-V4.1] Fix server crash on prompt-logprob and hidden-state requests under decoder SWA bounded replay
- Fix requested-token logprob handoff in P/D serving
- fix(speculative): prevent multi-gpu deadlock by rejecting grammar requests with DSpark + TP>1
- Fix reasoning token usage past speculative finish boundaries
- [Bug] DSpark + TP: grammar-constrained request batched with any other request deadlocks all ranks (overlap and non-overlap), GPUs spin in a collective
- [AMD][gfx1250] Retune sparse paged-prefill launch config for DSV4-Flash
- Docs
- Python not yet supported