Sparsity for neural network models based on sparsity attributes

A method comprising:

• receiving a first neural network model definition, the first neural network model definition specifying a neural network model comprising a set of tensors and a set of sparsity attribute values for elements of a tensor in the set of tensors;
• propagating the set of sparsity attribute values for the tensor to elements of a subset of the set of tensors to form a second neural network model definition;
• and
• generating the neural network model based on the second neural network model definition.

A system comprising:

• a set of processing units;
• and
• a non-transitory machine-readable medium storing instructions that when executed by at least one processing unit in the set of processing units cause the at least one processing unit to:
• receive a first neural network model definition, the first neural network model definition specifying a neural network model comprising a set of tensors and a set of sparsity attribute values for elements of a tensor in the set of tensors;
• propagate the set of sparsity attribute values for the tensor to elements of a subset of the set of tensors to form a second neural network model definition;
• and
• generate the neural network model based on the second neural network model definition.