modeld: skip redundant cast, reshape, and flatten (#35735)

* skip redundant cast, reshape, and flatten

* accidentally deleted a newline lol

selfdrive/modeld/dmonitoringmodeld.py

@@ -93,7 +93,7 @@ class ModelState:
       self.tensor_inputs['input_img'] = Tensor(self.frame.buffer_from_cl(input_img_cl).reshape((1, MODEL_WIDTH*MODEL_HEIGHT)), dtype=dtypes.uint8).realize()
 
 
-    output = self.model_run(**self.tensor_inputs).numpy().flatten()
+    output = self.model_run(**self.tensor_inputs).contiguous().realize().uop.base.buffer.numpy()
 
     t2 = time.perf_counter()
     return output, t2 - t1

selfdrive/modeld/modeld.py

@@ -163,14 +163,14 @@ class ModelState:
     if prepare_only:
       return None
 
-    self.vision_output = self.vision_run(**self.vision_inputs).numpy().flatten()
+    self.vision_output = self.vision_run(**self.vision_inputs).contiguous().realize().uop.base.buffer.numpy()
     vision_outputs_dict = self.parser.parse_vision_outputs(self.slice_outputs(self.vision_output, self.vision_output_slices))
 
     self.full_features_buffer[0,:-1] = self.full_features_buffer[0,1:]
     self.full_features_buffer[0,-1] = vision_outputs_dict['hidden_state'][0, :]
     self.numpy_inputs['features_buffer'][:] = self.full_features_buffer[0, self.temporal_idxs]
 
-    self.policy_output = self.policy_run(**self.policy_inputs).numpy().flatten()
+    self.policy_output = self.policy_run(**self.policy_inputs).contiguous().realize().uop.base.buffer.numpy()
     policy_outputs_dict = self.parser.parse_policy_outputs(self.slice_outputs(self.policy_output, self.policy_output_slices))
 
     # TODO model only uses last value now