fangwei123456/spikingjelly
SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.
Provides built-in ANN-to-SNN conversion, CUDA/Triton-accelerated neuron implementations, and support for neuromorphic datasets—enabling efficient training through gradient checkpointing and spike compression. Integrates with PyTorch's standard modules and ecosystem while offering NIR format support for cross-framework interoperability.
1,931 stars and 14,984 monthly downloads. Actively maintained with 2 commits in the last 30 days. Available on PyPI.
Stars
1,931
Forks
299
Language
Python
License
—
Category
Last pushed
Mar 12, 2026
Monthly downloads
14,984
Commits (30d)
2
Dependencies
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/fangwei123456/spikingjelly"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
neuromorphs/NIR
Neuromorphic Intermediate Representation reference implementation
jeshraghian/snntorch
Deep and online learning with spiking neural networks in Python
norse/norse
Deep learning with spiking neural networks (SNNs) in PyTorch.
BindsNET/bindsnet
Simulation of spiking neural networks (SNNs) using PyTorch.
cai4cai/torchsparsegradutils
A collection of utility functions to work with PyTorch sparse tensors