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
- [Feature] [KV events] Include the removal reason in `BlockRemoved`
- Add --tokenizer-worker-device cpu to run tokenizer workers without a CUDA context
- [PD-Disaggregation] Fix unbounded memory growth via orphan bootstrap_room lifecycle purge (#39428)
- [Bug] Block-FP8 Triton matmul silently accepts an unsupported K tile and returns wrong results
- fix(loader): let the unbalanced-loading barrier timeout be configured
- [Bugfix] Validate K tiles for block-FP8 Triton matmul
- [Perf] Add optional K-group unrolling for CUDA block-FP8 matmul
- fix(quantization): reject K tiles that cross block-fp8 quantization blocks
- [DSA][DCP] EAGLE / NextN chain drafting under decode context parallel (stacked on #39330)
- [DSA][DCP] HiCache host tier under decode context parallel (stacked on #39638)
- Docs
- Python not yet supported