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
- [Feat] sensenova_loop: Add multimodal Loop and mHC inference
- [Fix] [AMD] deepseek-v4: Respect AITER selection for Q-LoRA quantization
- [Fix] cookbook: fix the new page's playground facts and reproduction notes
- [Perf] [AMD] Qwen3.5: enable fused GDN decode unpack + Conv1D for ROCm platform
- [RFC] Add per-step TBO admission policy and fallback diagnostics
- [Doc] cookbook: Refresh DeepSeek-V4 B200 aggregate AgentX image
- [Bug] Tools + JSON-schema format cannot be combined: Kimi-K3 returns 400, glm47 / DeepSeek silently drop tool calls and invent the answer (breaks Codex --output-schema)
- [Feat] rust-server: Report the model's launch-time fields in /model_info
- [WIP][Feat] dflash: Serve MoE FFN drafts from the config's HF MoE fields
- [Fix] marlin: keep one block per SM in the MoE kernel
- Docs
- Python not yet supported