Patch-Based Stochastic Attention (efficient attention mecanism)
-
Updated
Jan 16, 2023 - Cuda
Patch-Based Stochastic Attention (efficient attention mecanism)
Custom CUDA kernel for transformer's attention mechanism and integrating it with pytorch
This is my GPU course final project in MICS600J. The main content is my attempt to handwrite the attention process.
Raw C/cuda implementation of 3d GAN
Add a description, image, and links to the attention-mechanism topic page so that developers can more easily learn about it.
To associate your repository with the attention-mechanism topic, visit your repo's landing page and select "manage topics."