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_rms_norm_rope_shape
def composite_rms_norm_rope_shape(input: T, weight: T, cos_vals: T, sin_vals: T) -> IndexList[T.rank]
Computes the output shape for the mo.composite.rms_norm_rope graph op.
Args:
- βinput (
T): Activation tensor normalized by RMS then rotated by RoPE; the last dimension must be even. - βweight (
T): Per-column scale weights applied after RMS normalization. - βcos_vals (
T): Cosine table used by the RoPE rotation, matchinginputrank. - βsin_vals (
T): Sine table used by the RoPE rotation, matchinginputrank.
Returns:
IndexList[T.rank]: The output shape, which matches the input shape.