ut coverage

Signed-off-by: violetch24 <[email protected]>

neural_compressor/torch/algorithms/static_quant/static_quant.py

@@ -79,7 +79,7 @@ def prepare(self, model, example_inputs, inplace=True, *args, **kwargs):
             )
             # update json file in ipex_config_path; map ipex op_name to pt op_name
             self.user_cfg = cfg_to_qconfig(self.quant_config, cfgs, op_infos_from_cfgs, output_tensor_id_op_name)
-        else:
+        else: # pragma: no cover
             model = model.to("xpu")
 
         model.eval()
@@ -109,7 +109,7 @@ def prepare(self, model, example_inputs, inplace=True, *args, **kwargs):
                     from torch.ao.quantization import QConfigMapping
 
                     static_qconfig = QConfigMapping().set_global(qconfig)
-                else:
+                else: # pragma: no cover
                     static_qconfig = QConfig(
                         activation=MinMaxObserver.with_args(qscheme=torch.per_tensor_affine, dtype=torch.quint8),
                         weight=PerChannelMinMaxObserver.with_args(

neural_compressor/torch/algorithms/static_quant/utility.py

@@ -163,7 +163,7 @@ def check_cfg_and_qconfig(user_cfg, cfgs, op_infos_from_cfgs, output_tensor_ids_
     return cfgs, ori_user_cfg
 
 
-def generate_xpu_qconfig(tune_cfg):
+def generate_xpu_qconfig(tune_cfg): # pragma: no cover
     # qconfig observer & config constants for ipex-xpu
     from torch.ao.quantization import HistogramObserver, MinMaxObserver, QConfig
 

neural_compressor/torch/quantization/config.py

@@ -1126,7 +1126,7 @@ def get_model_info_for_ipex(model: torch.nn.Module, example_inputs) -> List[Tupl
         _, _, _, _, model_info = get_quantizable_ops_recursively(model, example_inputs=example_inputs)
         return model_info
 
-    def get_model_info_for_ipex_xpu(self, model: torch.nn.Module) -> List[Tuple[str, Callable]]:
+    def get_model_info_for_ipex_xpu(self, model: torch.nn.Module) -> List[Tuple[str, Callable]]: # pragma: no cover
         if self.model_info:
             return self.model_info
         else: