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
- [diffusion] kernels: stop specializing on per-request sequence lengths
- [diffusion] release the allocator cache when the server idles, not per request
- Keep positional-readout requests out of chunked prefill
- [ROCm] GLM-5.2 decode path: decode-shaped MoE/MLA tiles, split speculative softmax, and bf16 GEMM routing
- [diffusion] video: let requests choose the libx264 preset
- [DFlash2] Keep the greedy selector walk in range for all-NaN score rows
- [Rust] Extract shared runtime.v1 protobuf bindings
- [PD][Fix] DSA indexer state is silently transferred into the wrong layers under PP
- [RFC] Dynamic Latent Consensus Governor for DeepSeek-R1 to Reduce KV-Cache Holding Time by 4.5x.
- [rust-renderer] Add /detokenize and /v1/detokenize
- Docs
- Python not yet supported