nickovchinnikov/microtorch
MicroTorch: A lightweight autograd library supporting both CPU and GPU execution, built on top of NumPy and CuPy. It enables efficient tensor operations with automatic differentiation.
This is a tool for developers who want to understand the inner workings of deep learning frameworks. It allows you to build neural networks and perform tensor computations with automatic differentiation, similar to PyTorch. You feed in numerical data and model architectures, and it helps you track gradients and update model parameters, whether you're using a CPU or GPU.
No commits in the last 6 months.
Use this if you are a developer or student eager to learn the fundamentals of automatic differentiation, backpropagation, and how deep learning libraries like PyTorch are built from the ground up.
Not ideal if you are looking for a production-ready deep learning framework with a vast ecosystem, extensive pre-trained models, or cutting-edge performance optimizations.
Stars
7
Forks
—
Language
Jupyter Notebook
License
—
Category
Last pushed
May 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nickovchinnikov/microtorch"
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