Running ML in the browser — WebAssembly / WebGPU.

medium

Answer

$Options: (1) TensorFlow.js: JS/WebGL/WebGPU backend; ONNX Runtime Web (WASM + WebGL / WebGPU).$
$(2) Transformers.js: run HuggingFace models in browser.$
$(3) WebLLM (MLC.ai): run LLM entirely in-browser via WebGPU.$
$Advantages: (1) no server cost.$
$(2) privacy (data never leaves device).$
$(3) offline capability.$
$(4) instant deploy.$
$Disadvantages: (1) model download size (users notice 100+ MB).$
$(2) limited GPU/memory (mobile).$
$Use cases: privacy-first ML, PWAs, demos.$

Check yourself — multiple choice

Random
TF.js / ONNX Runtime Web (WASM+WebGL/WebGPU) + Transformers.js (HF in browser) + WebLLM (LLM via WebGPU); pros: no server + privacy + offline + instant deploy; cons: download size + limited GPU/mem
Just JS
Not real

Browser ML: TF.js / ONNX Web / Transformers.js / WebLLM; privacy + no server.

#serving#infrastructure

215 interview questions in this topic.