cai4cai/torchsparsegradutils
A collection of utility functions to work with PyTorch sparse tensors
This collection of tools helps machine learning practitioners efficiently work with sparse data in PyTorch. It provides a more memory-efficient way to perform complex operations like matrix multiplication and solving linear systems, especially when dealing with very large datasets where most values are zero. Data scientists and researchers working on deep learning models with sparse inputs will find this useful for training models faster and with less memory.
Available on PyPI.
Use this if you are a machine learning researcher or data scientist building deep learning models in PyTorch that utilize sparse tensors, and you need to improve memory efficiency and computation speed during training, especially when dealing with gradient calculations.
Not ideal if your workflow primarily involves dense tensors or if you are not working with PyTorch's automatic differentiation system for gradient computations.
Stars
37
Forks
4
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cai4cai/torchsparsegradutils"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
fangwei123456/spikingjelly
SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.
neuromorphs/NIR
Neuromorphic Intermediate Representation reference implementation
BindsNET/bindsnet
Simulation of spiking neural networks (SNNs) using PyTorch.
norse/norse
Deep learning with spiking neural networks (SNNs) in PyTorch.
jeshraghian/snntorch
Deep and online learning with spiking neural networks in Python