On: Chrome ships WebGPU

[MuffinFlavored]

what would it take to python -> wasm -> webgpu for the entire existing webgpu ecosystem (all of the libraries around neural networks, torch, yada yada)

[grlass → MuffinFlavored]

The Apache TVM machine learning compiler has a WASM and WebGPU backend, and can import from most DNN frameworks. Here's a project running Stable Diffusion with webgpu and TVM [1].

Questions exist around post-and-pre-processing code in folks' Python stacks, with e.g. NumPy and opencv. There's some NumPy to JS transpilers out there, but those aren't feature complete or fully integrated.

[1] https://github.com/mlc-ai/web-stable-diffusion

[korijn → MuffinFlavored]

FYI you can already use webgpu directly in python, see https://github.com/pygfx/wgpu-py for webgpu wrappers and https://github.com/pygfx/pygfx for a more high level graphics library

[MuffinFlavored → korijn]

I think I meant to ask "how is machine learning support for things like neural networks instead of graphical 2D/3D operations with WebGPU"?

[korijn → MuffinFlavored]

Well, you could implement that on top of the wrappers as well I guess. Anyway!

[MuffinFlavored → korijn]

As in, I could, but a library/libraries doing so do not yet exist?

[korijn → MuffinFlavored]

Not that I know of!