metal-performance-shaders 开源项目推荐（34 个）

shu223 /iOS-10-Sampler

Code examples for new APIs of iOS 10.

tillahoffmann /jax-mps

A JAX backend for Apple Metal Performance Shaders (MPS), enabling GPU-accelerated JAX computations on Apple Silicon.

mrdbourke /mac-ml-speed-test

A few quick scripts focused on testing TensorFlow/PyTorch/Llama 2 on macOS.

jmanhype /vggt-mps

VGGT 3D 视觉代理，针对苹果硅芯片优化，配备金属性能着色器

imxieyi /MetalResize

Fast image interpolation using Metal

pedronahum /MetalHLO

Bringing StableHLO to Apple Silicon

Harperbot /metal-guard

Defensive layer for mlx / mlx-lm / mlx-vlm on Apple Silicon. Prevents IOGPUFamily kernel panics, SIGABRT, and Mac reboots from MLX inference. Includes a community-curated registry of known-panic models (KNOWN_PANIC_MODELS) with hardware contexts, root-cause hypotheses, and verified workarounds.

xmartlabs /gpgpu-comparison

该项目在 GitHub 上没有填写描述

imxieyi /CoreML-MPS

Run compiled CoreML(v1) model using MPSNN

KnowledgePending /Metal-Performance-Shaders

👨‍💻🔢🖼️Quick example of how Metal Performance Shaders can be used for Image Processing

StarxSky /tacotron2-JP

Base on "tacotron2-jpanese" builded & change

199-biotechnologies /ultrashape-mac

UltraShape 1.0 ported to Apple Silicon (MPS) -- high-fidelity 3D shape generation from images on Mac

williamxiewz /learn-metal

Metal

tudor-22 /MetalML

Metal GPU acceleration for scikit-learn on Mac. Drop-in sklearn API (fit, predict, transform) with Metal kernels and MPS for KMeans, Ridge, PCA, SVMs, kNN, Naive Bayes and random forests, plus automatic CPU fallback. pip install metalml

1rsh /installing-tf-and-torch-apple-silicon

This repository provides a guide for installing TensorFlow and PyTorch on Mac computers with Apple Silicon.

Gerzer /SwiftML

Train neural networks with hardware acceleration in Swift

TaewoooPark /mumax3-for-mac

Native Apple Silicon Metal port of mumax3, extending CUDA based micromagnetic simulation to macOS with MPSGraph FFT and validated physics compatibility.

TaewoooPark /mumax3-ultrafast

⚡ The fastest micromagnetic simulator on a Mac — 3.3×–30× faster and 5.9×–26× more energy-efficient than every other simulator that runs on Apple Silicon. Native Metal port of mumax³: unmodified .mx3, validated physics, 84M cells on a fanless MacBook Air.

199-biotechnologies /stream-diffvsr

Diffusion-based video super-resolution optimized for Apple Silicon (MPS). Upscale video 4x on Mac.

rgabhi2526 /mpsify

Run CUDA-hardcoded PyTorch repos on Apple Silicon (MPS) with zero source edits