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
- [Perf] qwen-image21: Pack BF16 gate/up projections on SM120
- [Fix] anthropic: Continue a trailing assistant message as a prefill
- [Fix] anthropic: Accept thinking enabled without budget_tokens
- [Perf] diffusion-sdpa: Use a lazy lower-right causal bias when Sq != Sk
- [Fix] debug: Align EAGLE dump steps with worker rounds
- [Fix] responses: Merge replayed tool calls into the preceding commentary message
- [Fix] dflash: Give the draft a private RoPE module
- [Perf] [NVIDIA] deepseek-v4.1: Zero the MegaAttention packed query once per forward, not per layer
- [Fix] rust_server: Keep idle attention-DP ranks from parking on their ring
- [Doc] [AMD] GLM-5.3: Enable MTP on MI355X and add the agentic recipe with the AMD monokernel
- Docs
- Python not yet supported