For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).
Mojo function
composite_matmul_fused_partial_rms_norm_shape
def composite_matmul_fused_partial_rms_norm_shape(input: T, weight: T, gamma: T) -> IndexList[T.rank]
Computes the output shape for the mo.composite.matmul_fused_partial_rms_norm graph op.
Args:
- โinput (
T): Input activation tensorxof the GEMV. - โweight (
T): Weight matrixWof shape(N, K)(rank 2). - โgamma (
T): RMS normalization scale vector (rank 1).
Returns:
IndexList[T.rank]: The output shape, which matches the input shape.