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] openai: Scrub server source paths from validation error responses
- [Perf] [NPU] allocator: Avoid device synchronization in alloc_extend
- [Fix] multimodal: bound image preprocessing GPU memory; reject decompression bombs
- [Feat] [Intel] Model-enabling: Enable MiMo-V2-Flash and MiMo-V2.5 on Xeon CPU
- [Feat] clover: Add native serving and self-speculative decoding
- [Test] watermarking: Add unit tests for config and detector
- [Fix] rust_extensions: Bound the Rust toolchain probe and run it one process at a time
- [MUSA] fa3: Add the full backend implementation
- [Fix] DSpark: Make the simulated-acceptance sampling skip opt-in
- [Perf] Hunyuan3D: Speed up shape export with GPU-side grid generation
- Docs
- Python not yet supported