Mojo function

bmm_sm100_blockwise_scaled_fp8

bmm_sm100_blockwise_scaled_fp8[a_layout: Layout, b_layout: Layout, c_layout: Layout, a_scales_layout: Layout, b_scales_layout: Layout, c_type: DType, a_type: DType, b_type: DType, a_scales_type: DType, b_scales_type: DType, *, transpose_b: Bool, umma_shape: IndexList[3], block_tile_shape: IndexList[3], a_swizzle: TensorMapSwizzle = TensorMapSwizzle.SWIZZLE_128B, b_swizzle: TensorMapSwizzle = TensorMapSwizzle.SWIZZLE_128B, elementwise_lambda_fn: Optional[elementwise_epilogue_type] = None](c: LayoutTensor[c_type, c_layout, c.origin, address_space=c.address_space, element_layout=c.element_layout, layout_int_type=c.layout_int_type, linear_idx_type=c.linear_idx_type, masked=c.masked, alignment=c.alignment], a: LayoutTensor[a_type, a_layout, a.origin, address_space=a.address_space, element_layout=a.element_layout, layout_int_type=a.layout_int_type, linear_idx_type=a.linear_idx_type, masked=a.masked, alignment=a.alignment], b: LayoutTensor[b_type, b_layout, b.origin, address_space=b.address_space, element_layout=b.element_layout, layout_int_type=b.layout_int_type, linear_idx_type=b.linear_idx_type, masked=b.masked, alignment=b.alignment], a_scales: LayoutTensor[a_scales_type, a_scales_layout, a_scales.origin, address_space=a_scales.address_space, element_layout=a_scales.element_layout, layout_int_type=a_scales.layout_int_type, linear_idx_type=a_scales.linear_idx_type, masked=a_scales.masked, alignment=a_scales.alignment], b_scales: LayoutTensor[b_scales_type, b_scales_layout, b_scales.origin, address_space=b_scales.address_space, element_layout=b_scales.element_layout, layout_int_type=b_scales.layout_int_type, linear_idx_type=b_scales.linear_idx_type, masked=b_scales.masked, alignment=b_scales.alignment], ctx: DeviceContext)