search

etrommer / torch-approx

GPU-accelerated Neural Network layers using Approximate Multiplications for PyTorch
https://etrommer.de/torch-approx
MIT License
6 stars 3 forks source link

Use PyTorch quantization interface #13

Closed etrommer closed 8 months ago

etrommer commented 10 months ago

TA currently uses its own Quantizer implementation. It would be cleaner to provide approximate layer implementation as subclasses of torch.ao.nn.qat.modules and use the observer/quantizer API that is provided by native PyTorch.