Pinned Loading

1. chitu chitu Public

   Forked from thu-pacman/chitu

   High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

   Python

2. dafeiyu dafeiyu Public

   大肥鱼 AI 虚拟主播：接入抖音弹幕与礼物，支持 AI 对话、语音播报、Live2D 动作表情、趣味贴脸和连续打字工位舞台，提供角色管理与一键启动。

   Python

3. hookprobe hookprobe Public

   Claude Code hooks 本地诊断工具：检查配置、测试脚本，探测真实会话中的 hook 回调。

   Go

4. kvpress kvpress Public

   Forked from NVIDIA/kvpress

   LLM KV cache compression made easy

   Python