mil-tokyo/wgpy
WebGPU/WebGL accelerated numpy-compatible array library for web browser
This project allows web developers to run heavy numerical computations, such as those found in deep learning, directly within a web browser using WebGL or WebGPU. It takes Python code that uses NumPy-like array operations and executes it efficiently on the user's graphics card, outputting the results back to Python. It's for web application developers building interactive, data-intensive browser experiences.
No commits in the last 6 months.
Use this if you need to perform high-performance numerical computing or deep learning inference directly in a web browser without relying on server-side processing.
Not ideal if your application doesn't involve intensive array computations or if you require full native GPU access beyond what WebGL/WebGPU offers.
Stars
45
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mil-tokyo/wgpy"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
tensorflow/tfjs
A WebGL accelerated JavaScript library for training and deploying ML models.
nnstreamer/api
Machine Learning API (Origin: C++: SNAP, C/C#: Tizen API, Java: Samsung-Research ML API). For...
microsoft/DMTK
Microsoft Distributed Machine Learning Toolkit
R-js/blasjs
Pure Javascript manually written :ok_hand: implementation of BLAS, Many numerical software...
tensorflow/tfjs-core
WebGL-accelerated ML // linear algebra // automatic differentiation for JavaScript.