DEV Community· skvrtyk·· 2 小時前AI 評分34
裝置端模型是部署產物，而非函式庫
Your On-Device Model Is a Deploy Artifact, Not a Library
AI 導讀
裝置端模型應視為部署產物，而非只需連結一次的函式庫；將量化模型打包進應用程式只需一個週末，維持 200,000 次安裝使用相容的應用程式、執行環境與權重組合一年，才是實際工作。模型檔案大小為 1.5–2 GB，作者觀察到，邊緣 AI 事故更多源於產物生命週期，而非模型質素。
正文
Bundling a quantized model into an app is a weekend. Keeping 200,000 installs on a compatible (app, runtime, weights) triple for a year is the actual work. The model is not a library you link once; it is a 1.5–2 GB artifact that ships on a schedule you don't control, to hardware you've never held, over networks that drop mid-transfer.
I've watched more edge-AI incidents come from artifact lifecycle than from model quality.
來源：DEV Community · dev.to