Mojo function

layer_norm_shape

layer_norm_shape[dtype: DType](input: TileTensor[dtype, address_space=input.address_space, linear_idx_type=input.linear_idx_type, element_size=input.element_size], gamma: TileTensor[dtype, address_space=gamma.address_space, linear_idx_type=gamma.linear_idx_type, element_size=gamma.element_size], beta: TileTensor[dtype, address_space=beta.address_space, linear_idx_type=beta.linear_idx_type, element_size=beta.element_size], epsilon: Scalar[dtype]) -> IndexList[TileTensor[dtype, input.LayoutType, input.origin, address_space=input.address_space, linear_idx_type=input.linear_idx_type, element_size=input.element_size].rank]

Compute the output shape of a layer_norm operation.

Parameters:

• ​dtype (DType): Type of the input tensors.

Args:

• ​input (TileTensor[dtype, address_space=input.address_space, linear_idx_type=input.linear_idx_type, element_size=input.element_size]): The input tensor.
• ​gamma (TileTensor[dtype, address_space=gamma.address_space, linear_idx_type=gamma.linear_idx_type, element_size=gamma.element_size]): The tensor for gamma coefficient.
• ​beta (TileTensor[dtype, address_space=beta.address_space, linear_idx_type=beta.linear_idx_type, element_size=beta.element_size]): The tensor for beta coefficient.
• ​epsilon (Scalar[dtype]): The tensor for epsilon coefficient.

Returns:

IndexList[TileTensor[dtype, input.LayoutType, input.origin, address_space=input.address_space, linear_idx_type=input.linear_idx_type, element_size=input.element_size].rank]: The output shape.

Was this page helpful?

Thank you! We'll create more content like this.

Thank you for helping us improve!

😔 What went wrong?

Some code doesn’t work

It includes inaccurate information

It's missing information I need

It was difficult to understand

Other

Submit