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

composite_matmul_fused_partial_rms_norm_shape

def composite_matmul_fused_partial_rms_norm_shape[dtype: DType, rank: Int](input: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=input.static_spec], weight: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=weight.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.composite.matmul_fused_partial_rms_norm graph op.

Parameters:

dtype (DType): Element type of the input and weight tensors.
rank (Int): Tensor rank of the input tensor.

Args:

input (ManagedTensorSlice[IOSpec[_, _].Input, static_spec=input.static_spec]): Input activation tensor x of the GEMV.
weight (ManagedTensorSlice[IOSpec[_, _].Input, static_spec=weight.static_spec]): Weight matrix W of shape (N, K) (rank 2).
gamma (ManagedTensorSlice[IOSpec[_, _].Input, static_spec=gamma.static_spec]): RMS normalization scale vector (rank 1).
epsilon (Float32): Small constant added to the squared mean before the reciprocal square root for numerical stability.
weight_offset (Scalar[dtype]): Reserved for API consistency with other RMS norm ops; not consumed by the shape function.

Returns:

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