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
- [WIP] Add initial Attention on Heads (AoH) runtime adapter
- fix(openai): skip the required-tool JSON fallback for non-JSON output
- [Scheduler] Expose DP-attention MLP sync transport
- [WIP] Restore KTransformers CPU-expert offload for DeepSeek-V4 on Ascend NPU
- [WIP] Fix AttributeError in compressed-tensors int8 MoE apply_weights (NPU)
- [Bug] DP-aware routing rank is dropped for OpenAI Responses API
- [Bug] Streaming: one unknown tool name discards or corrupts the other tool calls in the same parallel batch
- [Fix] Streaming: drop only the unknown tool call, not the batch around it
- [Fix] Gemma4: pick a deterministic-capable attention backend under --enable-deterministic-inference
- fix: stream MiMo tool call arguments incrementally
- Docs
- Python not yet supported