MicroQonv: Reshaping Convolution Tensors for Efficient Microscaling in Training and Inference
Microscaling quantization techniques are increasingly used to represent neural network parameters with 8 bits or fewer while preserving near-full precision accuracy. However, applying these methods efficiently in convolutional layers is not straightforward. A naive approach transfers full-precision weights and activations to processing units and quantizes each tensor twice, resulting in much more…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
