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
- [Tracking] DSpark in SGLang: roadmap
- [NPU] eagle3 support modelslim quarot
- [Bugfix][DSA] Fix num_splits (b+1) crash with DP-attention + speculative decode
- [Bug] FP8 KV-cache decode slowdown: unfused K/V quantization + per-layer Q conversion overhead
- [3/N] [spec] support STANDALONE spec decoding with DP attention
- fix(disagg): require extra-state transfer success for Mooncake prefill
- fix(sampling): handle NOT_LITERAL token in stop_regex max-length bound
- [ROCm] Add DeepSeek-V4 DSpark speculative decoding support for AMD GPU(MI350X / MI355X, gfx950)
- `page_blob_direct` layout for HiCache
- (fix) Prevent unknown HTTP paths from overloading Prometheus metrics generation
- Docs
- Python not yet supported