Mojo function

dual_gemv_kernel

dual_gemv_kernel[c_type: DType, c_shape: DimList, a_type: DType, a_shape: DimList, b_type: DType, b_shape: DimList, simd_width: Scalar[DType.uint], tile_m: Scalar[DType.uint], tile_n: Scalar[DType.uint], num_threads: Scalar[DType.uint], binary_lambda_fn: binary_fn_type, elementwise_lambda_fn: Optional[elementwise_epilogue_type] = None, s_type: DType = get_accum_type[c_type]()](c: NDBuffer[c_type, 2, MutAnyOrigin, c_shape], a: NDBuffer[a_type, 2, MutAnyOrigin, a_shape], b0: NDBuffer[b_type, 2, MutAnyOrigin, b_shape], b1: NDBuffer[b_type, 2, MutAnyOrigin, b_shape])