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
- [DeepSeek V4.1] an FP8 Tensor Core path for the FP4 grouped indexer
- Fix EAGLE draft EP dispatch when input_ids is None
- Reuse shared DFlash and DSpark verify metadata planning
- [HiCache] Preserve all MTP KV and recurrent state
- [Bug] DeepSeek V4/V3.2: DSML tool calls returned as content with no tool_calls (bare invoke, unterminated section, malformed sibling)
- [DSV4.1] Support PP x PD x DSpark
- [Bug] DP scheduler SIGQUIT terminates the DataParallelController instead of notifying the Engine
- [Bug] 0.5.20: `--quantization humming` crashes at weight load — `BlockQuantScaleParameter` has no attribute `format_ue8m0`
- [NPU] Add NPU cudagraph runner unit tests
- [Feature][DeepSeek-V4.1] Default prefill_decode_interval so long-context prefill cannot starve decode
- Docs
- Python not yet supported