MicroQonv: Reshaping Convolution Tensors for Efficient Microscaling in Training and Inference
MicroQonv reduces convolutional microscaling cost by quantizing tensors once before a modified im2col.
1 stories, newest first · one card per story
MicroQonv reduces convolutional microscaling cost by quantizing tensors once before a modified im2col.
Today 1.6K readers · 2.5K views · 792 reads · all time 189K views