The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

Squeeze-and-Excitation Networks

A GPU implementation of Convolutional Neural Nets in C++

Code for KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs

flash attention tutorial written in python, triton, cuda, cutlass

Unsupervised Learning of Video Representations using LSTMs

GPU implementation of a fast generalized ANS (asymmetric numeral system) entropy encoder and decoder, with extensions for lossless compression of numerical and other data types in HPC/ML applications.

CGBN: CUDA Accelerated Multiple Precision Arithmetic (Big Num) using Cooperative Groups

Code for Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference (CVPR2020)

CUDA implementation of data clustering using expectation maximization with a Gaussian mixture model. Supports multiple GPUs on a single node.