# ExecuTorch adds a WebGPU backend for running PyTorch models in browsers

> Original title: ExecuTorch WebGPU: PyTorch Models on the GPU, in the Browser

- Source: PyTorch Blog
- Published: 2026-11-10T22:15:07.000Z
- Bad Influence: https://badinfluence.news/items/d2p258glvfhvfhzsvj5o7d6j1
- Original: https://pytorch.org/blog/executorch-webgpu-pytorch-models-on-the-gpu-in-the-browser/

## Summary

PyTorch says ExecuTorch now runs PyTorch models on the GPU in WebGPU-enabled browsers, using a .pte file exported with torch.export and no conversion to another format. The company reports WebGPU is 4–7× faster than the CPU path (WebAssembly with XNNPACK) on prefill and 2–10× faster on decode, measured in Chrome on an Apple M1 Pro. The backend is in early development, with inference running locally in the browser tab.

## Why it matters

The post shows how a PyTorch model moves from a single export to in-browser GPU inference, with benchmark figures against the existing CPU path.