CUDA Kernels

A collection of CUDA kernels for PyTorch

Kernels implemented to date

• Matrix Multiplication of PyTorch Tensors (matmul.ipynb)
• Element-wise vector addition of C float arrays (vec_add.cpp)
• Color to Grayscale of C image array (color_to_grayscale_image.cpp)
• Image blur kernel (image_blur_kernel.cpp)