NumPy & SciPy for GPU

Simple Python version management

realtime latent world model inference demo

Master programming by recreating your favorite technologies from scratch.

Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search

Optimizing SGEMM kernel functions on NVIDIA GPUs to a close-to-cuBLAS performance.

Fast CUDA matrix multiplication from scratch

The simplest but fast implementation of matrix multiplication in CUDA.

Simple and fast JSON database

🐠 Babel is a compiler for writing next generation JavaScript.

A set of hands-on tutorials for CUDA programming

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

Development repository for the Triton language and compiler

ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization

Clone this repo to build Frida

The Reliable USB Formatting Utility

Powerful android apk editor - aapt/aapt2 independent

APK Downloader for Google Play

Grok open release

Tools for handling firmwares of DJI products, with focus on quadcopters.

Pytorch implementation of convolutional neural network visualization techniques

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Code for the paper Hybrid Spectrogram and Waveform Source Separation

Video stabilization using gyroscope data

You like pytorch? You like micrograd? You love tinygrad! ❤️

Real-time night sky rendering and planetarium in Swift 4 with native SceneKit and Metal.

stock market models - have fun

Keep passwords and other sensitive information out of your inboxes and chat logs.