Mojo function

quantize_dynamic_scaled_async_fp4_kernel

quantize_dynamic_scaled_async_fp4_kernel[input_dtype: DType, input_tile_rank: Int, input_tile_shape: IndexList[input_tile_rank], input_desc_shape: IndexList[input_tile_rank], output_dtype: DType, output_tile_rank: Int, output_tile_shape: IndexList[output_tile_rank], output_desc_shape: IndexList[output_tile_rank], scales_dtype: DType, scales_tile_rank: Int, scales_tile_shape: IndexList[scales_tile_rank], scales_desc_shape: IndexList[scales_tile_rank], input_swizzle_mode: TensorMapSwizzle, output_swizzle_mode: TensorMapSwizzle, scales_swizzle_mode: TensorMapSwizzle, SF_VECTOR_SIZE: UInt, NUM_PIPELINES_STAGES: UInt](input_tma_op: TMATensorTile[input_dtype, input_tile_rank, input_tile_shape, input_desc_shape], output_tma_op: TMATensorTile[output_dtype, output_tile_rank, output_tile_shape, output_desc_shape], scales_tma_op: TMATensorTile[scales_dtype, scales_tile_rank, scales_tile_shape, scales_desc_shape], tensor_sf: Float32)