A deep learning library for spiking neural networks which is based on PyTorch, focuses on fast training and supports inference on neuromorphic hardware.
This reduces overall run time of the CI pipeline. This is because normally pip install torch will install CUDA versions by default, but the CI containers don't have GPU access anyway
This reduces overall run time of the CI pipeline. This is because normally
pip install torch
will install CUDA versions by default, but the CI containers don't have GPU access anyway