Fix PyTorch stateful RNN/LSTM gradient computation error resolves #20875

keras/src/layers/rnn/rnn.py

@@ -331,6 +331,14 @@ def inner_loop(self, sequences, initial_state, mask, training=False):
             cell_kwargs["training"] = training
 
         def step(inputs, states):
+            """
+            Create new tensor copies when using PyTorch backend
+            with stateful=True. This prevents in-place modifications
+            that would otherwise break PyTorch's autograd functionality
+            by modifying tensors needed for gradient computation.
+            """
+            if backend.backend() == "torch" and self.stateful:
+                states = tree.map_structure(ops.copy, states)
             output, new_states = self.cell(inputs, states, **cell_kwargs)
             if not tree.is_nested(new_states):
                 new_states = [new_states]

keras/src/layers/rnn/rnn_test.py

@@ -383,4 +383,19 @@ def test_serialization(self):
         layer = layers.RNN(OneStateRNNCell(2), return_sequences=False)
         self.run_class_serialization_test(layer)
 
+    @pytest.mark.torch
+    def test_stateful_state_copying(self):
+        sequence = np.ones((1, 2, 3))
+        layer = layers.RNN(
+            TwoStatesRNNCell(2),
+            stateful=True,
+            return_state=True,
+        )
+        _, state1, state2 = layer(sequence)
+
+        self.assertIsNot(state1, layer.states[0])
+        self.assertIsNot(state2, layer.states[1])
+        self.assertAllClose(state1, layer.states[0])
+        self.assertAllClose(state2, layer.states[1])
+
     # TODO: test masking