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
- UnifiedRadixCache: implement query_storage_hit_length for decode-side HiCache
- [Feature] Streaming ASR: sliding window, server-side VAD, and segment-streaming mode
- [Feature] DFLASH EAGLE-style draft-tree verification
- [misc] Debug dev branch
- [Bug] Dynamic LoRA loading is effectively unsupported with --tokenizer-worker-num > 1 (per-worker registry, no cross-worker sync)
- [Bug] Fix DP-attention state-capturer crash on cuda_graph_batch=None (#30712)
- Fix infinite thinking loop caused by cross-chunk tag truncation in Qwen3 streaming
- modify benchmark for prefix cache case
- feat(dsa): add SM89 FP8 paged indexer operator
- Fix MXFP4 expert zero weight loading
- Docs
- Python not yet supported