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
- [Model] Support Qwen3.5 text checkpoints with language_model prefix
- Fix DFLASH compact draft cache: seq_lens_cpu must include the verify block
- [MLX] Support context-managed Metal profiling
- [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
- [HiSparse] Avoid host synchronization in eager backup
- [AMD][DeepSeek-V4.1] Fix server crash on prompt-logprob and hidden-state requests under decoder SWA bounded replay
- [MemCache] refactor: require an anchored lock receipt for non-root releases
- Docs
- Python not yet supported