Skip to main content

Mojo function

rms_norm_cpu

rms_norm_cpu[dtype: DType, //, input_fn: fn[Int](Int, Int) capturing -> SIMD[dtype, $0], output_fn: fn[Int, Int](Int, Int, SIMD[dtype, $0]) capturing -> None, multiply_before_cast: Bool](gamma: LayoutTensor[dtype, layout, origin, address_space=address_space, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], epsilon: Scalar[dtype], weight_offset: Scalar[dtype], out_shape: IndexList[2])

rms_norm_cpu[dtype: DType, rank: Int, //, input_fn: fn[Int, Int](IndexList[$1]) capturing -> SIMD[dtype, $0], output_fn: fn[Int, Int](IndexList[rank], SIMD[dtype, $0]) capturing -> None, multiply_before_cast: Bool](shape: IndexList[rank], gamma: LayoutTensor[dtype, layout, origin, address_space=address_space, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], epsilon: Scalar[dtype], weight_offset: Scalar[dtype])

Was this page helpful?