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
- [Bug] `top_k`, `logprobs` and `n` have no upper bound, one request can DoS the server
- [CPU] Routes all_gather_into_tensor and reduce_scatter_tensor to shm kernels
- Npu/ple offload
- fix: wrap SessionParams TypeError to ValueError and add validation unit tests
- [DeepSeek V4.1] Use DeepSelect for Hopper full top-k decode.
- [Bug] Two concurrent requests using DisallowedTokensLogitsProcessor with different token_ids crash the server
- docs: remove dead development guide link from CONTRIBUTING
- [Bug] A worker whose launcher died during startup sends SIGQUIT to PID 1
- Build SWA window kv buffers for the EAGLE draft-extend cuda-graph path
- [RFC] RuntimeContext as the configuration API
- Docs
- Python not yet supported