ExecuTorch WebGPU Release
The story so far
ExecuTorch has released the WebGPU backend, enabling PyTorch models to run directly in WebGPU browsers without converting frameworks. This technology ensures all operations are performed locally, without data leakage. Performance-wise, the WebGPU path is 4–7 times faster than ExecuTorch's CPU path (WebAssembly + XNNPACK) on prefill tasks and 2–10 times faster on decode tasks. PyTorch models now run on the browser GPU via ExecuTorch, without needing to be converted to other framework formats.
AI-written from the reports · Updated 8 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- PyTorch BlogExecuTorch WebGPU: PyTorch Models on the GPU, in the Browser
PyTorch models run on WebGPU in browsers via ExecuTorch without converting framework formats. Export as ExecuTorch .pte files and run on any WebGPU browser using the new ExecuTorch WebGPU backend.
Heat over time
- Now
- 3
- Peak
- 512 Nov, 06:00
- 24h change
- -50%
Hover or tap the chart to see each hour; use the arrow keys on a keyboard.