94% on CIFAR-10 in 2.6 seconds 💨 96% in 27 seconds

[ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule

Flash Attention Implementation with Multiple Backend Support and Sharding This module provides a flexible implementation of Flash Attention with support for different backends (GPU, TPU, CPU) and p…

Accelerate, Optimize performance with streamlined training and serving options with JAX.

Dolomite Engine is a library for pretraining/finetuning LLMs

LogiTorch is a PyTorch-based library for logical reasoning on natural language

The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models

Efficient optimizers

glebooru

PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡

Transform datasets at scale. Optimize datasets for fast AI model training.

Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.

Gin provides a lightweight configuration framework for Python

Configurable and simple file manager for X11

Painter & SegGPT Series: Vision Foundation Models from BAAI

A minimal implementation of diffusion models for text generation

mouse-based window manager that can tile windows inside floating containers

🎶 a fast and simple multimedia fileserver

wip port of raylib 5.1-dev to 9front

an adaptable text editor

9Front collection of programs, scripts, and notes

A Loom implementation in Obsidian

command loom interface

es: a shell with higher-order functions

A simple and lightweight Linux® distribution based on musl libc and toybox

Simple Application Sandboxing

Implementation of Slot Attention from GoogleAI

Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT