Image-text retrieval with EmbeddingGemma 2's vision tower, running in the browser on WebGPU
英文标题：Image-text retrieval with EmbeddingGemma 2's vision tower, running in the browser on WebGPU
EmbeddingGemma 2 came out this week. It maps images and text into one 768-dim space, so you can search photos by describing them. I ported its text and vision towers to ruNNtime, a WebGPU inference library in TypeScript, and made a small photo gallery where search runs entirely on your GPU in
打开原文相关 3 · 机会 2
中文
EmbeddingGemma 2 came out this week. It maps images and text into one 768-dim space, so you can search photos by describing them. I ported its text and vision towers to ruNNtime, a WebGPU inference library in TypeScript, and made a small photo gallery where search runs entirely on your GPU in
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
EmbeddingGemma 2 came out this week. It maps images and text into one 768-dim space, so you can search photos by describing them. I ported its text and vision towers to ruNNtime, a WebGPU inference library in TypeScript, and made a small photo gallery where search runs entirely on your GPU in