etrommer/torch-approx
GPU-accelerated Neural Network layers using Approximate Multiplications for PyTorch
This project helps machine learning engineers accelerate their neural network training and inference workflows. By using approximate multiplications in their PyTorch models, they can achieve faster computations and potentially reduce energy consumption. It takes standard neural network models and outputs functionally similar models that run more efficiently on GPUs.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher looking to speed up your PyTorch neural network operations on GPUs, especially for deep learning model deployment or large-scale training.
Not ideal if your primary concern is absolute numerical precision or if you are not working with GPU-accelerated PyTorch neural networks.
Stars
10
Forks
4
Language
Python
License
MIT
Category
Last pushed
Mar 04, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/etrommer/torch-approx"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pymc-devs/pytensor
PyTensor allows you to define, optimize, and efficiently evaluate mathematical expressions...
arogozhnikov/einops
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
lava-nc/lava-dl
Deep Learning library for Lava
tensorly/tensorly
TensorLy: Tensor Learning in Python.
tensorpack/tensorpack
A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility