Mojo function

sm100_warp_specialized_blockwise_fp8

sm100_warp_specialized_blockwise_fp8[c_type: DType, c_layout: Layout, a_type: DType, a_layout: Layout, b_type: DType, b_layout: Layout, transpose_b: Bool, a_scales_layout: Layout, b_scales_layout: Layout, a_scales_type: DType, b_scales_type: DType, *, config: MatmulConfig[a_type, b_type, c_type, transpose_b], cta_group: Int = 1, num_clc_pipeline_stages: UInt = UInt(2), num_pipeline_stages: UInt = UInt(4)](c: LayoutTensor[c_type, c_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, a_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, b_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, a_scales_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, b_scales_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)