Sparsity-aware deep learning inference runtime for CPUs
-
Updated
Jun 25, 2024 - Python
Sparsity-aware deep learning inference runtime for CPUs
Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
Code for CRATE (Coding RAte reduction TransformEr).
Complex-valued neural networks for pytorch and Variational Dropout for real and complex layers.
(Unstructured) Weight Pruning via Adaptive Sparsity Loss
Feather is a module that enables effective sparsification of neural networks during training. This repository accompanies the paper "Feather: An Elegant Solution to Effective DNN Sparsification" (BMVC2023).
The communication efficiency of federated learning is improved by sparsifying the parameters uploaded by the clients.
Add a description, image, and links to the sparsification topic page so that developers can more easily learn about it.
To associate your repository with the sparsification topic, visit your repo's landing page and select "manage topics."