How do I implement recurrent activations for LSTM/GRU cells in Pytorch?

Question

Although Tensorflow has simple parameters with which I can initialize the recurrent activation of a GRU or LSTM cell, Pytorch does not.

What is the best way to add recurrent activation in pytorch?

class SomeGruModule(Module):
    def __init__(self):
        super(SomeGruModule, self).__init__()
    
        self.gru = GRU(input_size=10, hidden_size=30)
    
    def forward(self, temporal_data):
        return self.gru(temporal_data)