I am developing a multilayer perceptron, and I have the following method inside of the class MultiLayerPerceptron, and I would like to configure this method to run on a GPU, I would like to do this using numba, using the @cuda.jit decorator, but I am not sure how to specify the kernel configuration. Also it it neccesary for me to have NVIDIA cuda api installed?

    def backprop(self, x, y):
        nabla_b = [np.zeros(b.shape) for b in self.biases]
        nabla_w = [np.zeros(w.shape) for w in self.weights]
        activation = x
        activations = [x] # list to store all the activations, layer by layer
        zs = [] # list to store all the z vectors, layer by layer
        for b, w in zip(self.biases, self.weights):
            z = np.dot(w, activation)+b
            zs.append(z)
            activation = self.apply_activation(z)
            activations.append(activation)
        delta = self.cost_function_derivative(activations[-1], y) *self.sigmoid_function_prime2(zs[-1])
        nabla_b[-1] = delta
        nabla_w[-1] = np.dot(delta, activations[-2].transpose())
        for l in range(2, self.num_layers): 
            z = zs[-l]
            sp = self.apply_activation_derivative(z)
            delta = np.dot(self.weights[-l+1].transpose(), delta) * sp
            nabla_b[-l] = delta
            nabla_w[-l] = np.dot(delta, activations[-l-1].transpose())
        return (nabla_b, nabla_w)