chore: activate input compression for encrypted data-frames

src/concrete/ml/pandas/_development.py

@@ -164,12 +164,12 @@ def save_client_server(client_path: Path = CLIENT_PATH, server_path: Path = SERV
     # Get the input-set and circuit generating functions
     inputset = config["get_inputset"]()
     cp_func = config["to_compile"]
-    compilation_configuration = Configuration(compress_evaluation_keys=True)
+    configuration = Configuration(
+        composable=True, compress_evaluation_keys=True, compress_input_ciphertexts=True
+    )
 
     # Compile the circuit and allow it to be composable with itself
-    merge_circuit = cp_func.compile(
-        inputset, composable=True, configuration=compilation_configuration
-    )
+    merge_circuit = cp_func.compile(inputset, configuration=configuration)
 
     # Save the client and server files using the MLIR
     merge_circuit.client.save(client_path)

src/concrete/ml/sklearn/linear_model.py

@@ -347,7 +347,7 @@ def _get_training_quantized_module(
         # Enable the underlying FHE circuit to be composed with itself
         # This feature is used in order to be able to iterate in the clear n times without having
         # to encrypt/decrypt the weight/bias values between each loop
-        configuration = Configuration(composable=True, compress_evaluation_keys=True)
+        configuration = Configuration(composable=True)
 
         composition_mapping = {0: 2, 1: 3}
 

tests/torch/test_hybrid_converter.py

@@ -37,17 +37,9 @@ def run_hybrid_llm_test(
 ):
     """Run the test for any model with its private module names."""
 
-    # Multi-parameter strategy is used in order to speed-up the FHE executions
-    configuration = Configuration(
-        single_precision=False,
-        compress_input_ciphertexts=True,
-    )
-
     # Create a hybrid model
     hybrid_model = HybridFHEModel(model, module_names)
-    hybrid_model.compile_model(
-        inputs, p_error=0.01, n_bits=8, rounding_threshold_bits=8, configuration=configuration
-    )
+    hybrid_model.compile_model(inputs, p_error=0.01, n_bits=8, rounding_threshold_bits=8)
 
     # Check we can run the simulate locally
     logits_simulate = hybrid_model(inputs, fhe="simulate").logits