Flyweight: open-source C++/CUDA engine for running MoE models bigger than your VRAM on one GPU + system RAM. First PyPI release, looking for contributors.

Been building this for a few months, mostly for myself, and it just got a proper release so figured I'd post it. It's a native GGUF inference runtime with OpenAI/Anthropic-compatible APIs and a chat UI. The whole point is one consumer NVIDIA card + lots of RAM: MoE models that don't fit in VRAM run

中文全文翻译正在补齐，可先查看下方英文原文。

Been building this for a few months, mostly for myself, and it just got a proper release so figured I'd post it. It's a native GGUF inference runtime with OpenAI/Anthropic-compatible APIs and a chat UI. The whole point is one consumer NVIDIA card + lots of RAM: MoE models that don't fit in VRAM run