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_rms_norm_shape

def reduce_rms_norm_shape[dtype: DType, rank: Int](input: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=input.static_spec], gamma: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=gamma.static_spec], epsilon: Float32, weight_offset: Scalar[dtype]) -> IndexList[rank]

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

Parameters:

dtype (DType): Element type of the input and gamma 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 the last dimension.
gamma (ManagedTensorSlice[IOSpec[_, _].Input, static_spec=gamma.static_spec]): Per-column scale weights applied after normalization.
epsilon (Float32): Small constant added inside the RMS normalization square root for numerical stability.
weight_offset (Scalar[dtype]): Scalar offset added to gamma before scaling.

Returns:

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