GPU Computing
CUDA Voxelizer to convert polygon meshes into annotated voxel grids
stdgpu: Efficient STL-like Data Structures on the GPU
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows
Development repository for the Triton language and compiler
Point Pair Features are used for rigid object detection in point clouds
Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
Sample codes for my CUDA programming book
An efficient C++17 GPU numerical computing library with Python-like syntax
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing …
[ARCHIVED] The C++ Standard Library for your entire system. See https://github.com/NVIDIA/cccl
A Python framework for accelerated simulation, data generation and spatial computing.