Mojo function

batched_matmul_dynamic_scaled_fp8_naive

batched_matmul_dynamic_scaled_fp8_naive[c_type: DType, a_type: DType, b_type: DType, a_scales_type: DType, b_scales_type: DType, //, *, scales_granularity_mnk: IndexList[3], transpose_b: Bool = False](c_: LayoutTensor[c_type, 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], a_: LayoutTensor[a_type, 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], b_: LayoutTensor[b_type, 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], a_scales_: LayoutTensor[a_scales_type, 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], b_scales_: LayoutTensor[b_scales_type, 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], ctx: DeviceContext)