# latency of a neural network at the expense of some model accuracy. It is # also known as **fine-grained structured sparsity** or **2:4 structured # sparsity**. # question-answering model to be 2:4 ...

Embeds scalar timesteps into vector representations. t: a 1-D Tensor of N indices, one per batch element. These may be fractional. dim: the dimension of the output. max_period: controls the minimum ...