Vulkan Python Packages

mnn

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

ncnn

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

pnnx

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

wgpu

WebGPU for Python

slangtorch

Making it easier to work with shaders

quadrants

High-performance multi-platform compiler for physics simulation

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.

apache-tvm

Open Machine Learning Compiler Framework

vulkan

The ultimate Python binding for Vulkan API

gstaichi

High-performance multi-platform compiler for physics simulation

openstl

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

glad2

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

iree-tools-tflite

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

iree-tools-tf

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

linux-rt-upscaler

A real-time SRCNN upscaler for any X-Window.

glad

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

llama-cpp-py-sync

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

fastplotlib

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

iree-runtime

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

forge3d

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

orkid

Orkid Media Engine (C++/Lua/Python3/Linux/MacOs/OpenVR/Vulkan)

vapoursynth-mlrt-ort-cuda

Efficient CPU/GPU ML Runtimes for VapourSynth (with built-in support for waifu2x, DPIR, RealESRGANv2/v3, Real-CUGAN, RIFE, SCUNet, ArtCNN and more!)