Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

Cramming the training of a (BERT-type) language model into limited compute.

Practice your pandas skills!

ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training

Interpretable Evaluation for AI Systems

Official code for "VFlow: More Expressive Generative Flows with Variational Data Augmentation" (ICML 2020)

Binarize convolutional neural networks using pytorch 🔥

An elegant PyTorch deep reinforcement learning library.

ReActNet: Towards Precise Binary NeuralNetwork with Generalized Activation Functions. In ECCV 2020.

Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm. In ECCV 2018 and IJCV

code for the paper "A Statistical Framework for Low-bitwidth Training of Deep Neural Networks"

Zhusuan with backend PaddlePaddle

Refining continuous-in-depth neural networks

Keep an Eye on Defects Inspection.

Summary, Code for Deep Neural Network Quantization

Unofficial implementation of LSQ-Net, a neural network quantization framework

Low Precision Arithmetic Simulation in PyTorch

东北方言编程语言

A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

Open deep learning compiler stack for cpu, gpu and specialized accelerators

Performance-optimized wheels for TensorFlow (SSE, AVX, FMA, XLA, MPI)

Code corresponding to the paper "Adversarial Examples are not Easily Detected..."

source code of the paper Graphical Generative Adversarial Networks

Big Topic Model is a fast engine for running large-scale Topic Models.

Population matching discrepancy

Stochastic training of graph convolutional networks

MMD-GAN: Towards Deeper Understanding of Moment Matching Network

LINE: Large-scale information network embedding