Search Packages

mnn

MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

pnnx

ncnn is a high-performance neural network inference framework optimized for the mobile platform

ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

slangtorch

Making it easier to work with shaders

wgpu

WebGPU for Python

pygfx

Powerful and versatile visualization for Python.

iree-base-compiler

A retargetable MLIR-based machine learning compiler and runtime toolkit.

iree-base-runtime

A retargetable MLIR-based machine learning compiler and runtime toolkit.

fastplotlib

Next-gen fast plotting library running on WGPU using the pygfx rendering engine

vulkan

The ultimate Python binding for Vulkan API

openstl

The fastest and most intuitive library to manipulate STL files (stereolithography) for C++ and Python, header-only.

iree-tools-tf

A retargetable MLIR-based machine learning compiler and runtime toolkit.

iree-tools-tflite

A retargetable MLIR-based machine learning compiler and runtime toolkit.

linux-rt-upscaler

A real‑time AI upscaler for any application window on GNU/Linux.

llama-cpp-py-sync

Auto-synced CFFI ABI python bindings for llama.cpp with prebuilt wheels (CPU/CUDA/Vulkan/Metal).

iree-runtime

A retargetable MLIR-based machine learning compiler and runtime toolkit.

glad

Multi-Language Vulkan/GL/GLES/EGL/GLX/WGL Loader-Generator based on the official specs.

glad2

Multi-Language Vulkan/GL/GLES/EGL/GLX/WGL Loader-Generator based on the official specs.

ogre-python

Object-Oriented Graphics Rendering Engine - python package

pyiced

Bindings for Iced, a cross-platform GUI library focused on simplicity. Inspired by Elm.

forge3d

Rust‑first, cross‑platform wgpu/WebGPU renderer exposed to Python for fast, headless 3D rendering. Built in Rust, shipped as Python wheels.

itk-vkfft

VkFFT backends for ITK FFT classes.

xtc-tvm-python-bindings

Open Machine Learning Compiler Framework

grilly

GPU-accelerated neural network operations using Vulkan compute shaders