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
- [sglang-miles] Fix empty logprob tensors in mixed scoring/decode batches
- [Bug] NIXL staging reuses the send buffer too early and repeats completed sends
- fix(nixl): prevent early staging buffer reuse and duplicate sends
- [AMD][DSv4] Add experimental AITER FP4 streaming TopK
- [AMD] Remove invalid escape warning in RPD utils
- [NPU] Reduce nightly runtime for GLM-5.2 and Kimi-K3 accuracy cases
- Support Marlin MoE with DeepEP normal and low-latency dispatch
- [Bug] Decode running batch pinned at `max_running_requests - 1` under Chunked Prefill
- [sglang-miles] Add sparse per-position requested-token scoring
- [Docs] GLM-5.3-Flash cookbook: fix DFlash2 note, deprecated flags, add NVFP4 DCP4 row
- Docs
- Python not yet supported