For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).

Mojo function

reduce_group_norm_shape

def reduce_group_norm_shape[dtype: DType, rank: Int](input: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=input.static_spec], gamma: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=gamma.static_spec], beta: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=beta.static_spec], epsilon: Float32, num_groups: Int32) -> IndexList[rank]

Computes the output shape for the mo.reduce.group_norm graph op.

Parameters:

dtype (DType): Element type of the input, gamma, and beta tensors.
rank (Int): Number of dimensions in the input and output tensors.

Args:

input (ManagedTensorSlice[IOSpec[_, _].Input, static_spec=input.static_spec]): Input tensor normalized across grouped channels.
gamma (ManagedTensorSlice[IOSpec[_, _].Input, static_spec=gamma.static_spec]): Per-channel scale weights applied after normalization.
beta (ManagedTensorSlice[IOSpec[_, _].Input, static_spec=beta.static_spec]): Per-channel shift weights applied after scaling.
epsilon (Float32): Small constant added inside the normalization variance for numerical stability.
num_groups (Int32): Number of groups the channel dimension is split into for computing mean and variance.

Returns:

IndexList[rank]: The output shape, which matches the input shape.