PrismML 将小型 LLM 移植到 Qualcomm 智能眼镜上
PrismML brings its tiny LLMs to Qualcomm-powered smart glasses
精选理由
PrismML 把自家小模型塞进 Qualcomm 智能眼镜里跑，走的是端侧开源路线，做 AR 眼镜开发的话值得看看
PrismML 宣布其小型 LLM 可以在搭载 Qualcomm 芯片的智能眼镜上本地运行。公司定位是做开放权重的端侧 AI，充分利用设备已有的算力，不依赖云端。这意味着语音助手、翻译等任务可以在眼镜本地完成，降低延迟并减少隐私顾虑。
原文 · techcrunch
PrismML brings its tiny LLMs to Qualcomm-powered smart glasses
Prism's larger goal is open-weight AI that runs on devices and makes better use of the computing power they already have.
