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
- [ROCm] Fix gfx942 LDS overflow in DSA bf16 decode under dp-attention
- Bind streaming abort cleanup to request lifecycle
- Normalize the deprecated nsa attention backend alias to dsa
- [SM120] dspark: widen SWA index width to an instantiated sparse-MLA shape
- AMD Development Roadmap (2026 Q3)
- fix: broadcast EAGLE draft-side sampling across TP ranks on ROCm
- [diffusion][AMD] Add support for new quantized attention backends for GFX942/GFX950
- fix: unblock the DSA prefill split-op graph surface on HIP (is_cuda gate)
- fix: guard top-logprobs and token-ids logprob rows against missing data
- [RFC] Orchestrator-facing Elastic EP lifecycle contract
- Docs
- Python not yet supported