pygfx/wgpu-py

WebGPU for Python

What it solves

It provides Python with a modern, reliable GPU API that is easier to use than low-level APIs like Vulkan, Metal, or DX12, while being more up-to-date than OpenGL. This allows developers to build high-performance visualization and GPU compute applications directly in Python.

How it works

wgpu-py acts as a Python wrapper for wgpu-native, exposing a Pythonic API that closely follows the WebGPU specification. It supports both synchronous (blocking) functions for general ease of use and asynchronous versions for integration with frameworks like Asyncio or Trio.

Who it’s for

It is designed for developers creating graphics engines, visualization libraries, or GPU-accelerated compute tools who want a standardized, cross-platform API for Windows, Linux, and MacOS.

Highlights

  • WebGPU Standard: Implements the next-generation GPU API designed to succeed WebGL and OpenGL.
  • Cross-Platform: Full support for Windows, Linux (x86 and aarch64), and MacOS (Intel and M1).
  • Broad Ecosystem: Serves as the foundation for projects like the pygfx render engine and the tinygrad deep learning framework.
  • Flexible Rendering: Can be integrated with various GUI toolkits via rendercanvas for screen rendering.

Related

  • Project
    AnswerDotAI/gpu.cpp

    A lightweight C++20 interface for GPU compute via WebGPU that simplifies shader dispatch and data movement across native and browser environments.

  • Project
    runpod/runpod-python

    The official Python library for RunPod, providing an SDK to build serverless AI workers and a GraphQL wrapper to manage GPU cloud pods and endpoints.

  • Project
    inducer/pycuda

    PyCUDA is a Python wrapper for Nvidia's CUDA API that enables high-performance parallel computation on GPUs with automatic memory management and C++ speed.

  • Project
    KomputeProject/kompute

    A cross-vendor GPU compute framework based on Vulkan that enables high-performance acceleration for machine learning and data processing across AMD, NVIDIA, and Qualcomm hardware.

  • Project
    rapidsai/cugraph

    A collection of GPU-accelerated graph analytics packages that enable the creation and manipulation of graphs and the execution of scalable graph algorithms.