disable `torch.jit` when using Ascend NPUs

modeling_chatglm.py

@@ -21,7 +21,7 @@ from transformers.modeling_outputs import (
     SequenceClassifierOutputWithPast,
 )
 from transformers.modeling_utils import PreTrainedModel
-from transformers.utils import logging
+from transformers.utils import logging, is_torch_npu_available
 from transformers.generation.logits_process import LogitsProcessor
 from transformers.generation.utils import LogitsProcessorList, StoppingCriteriaList, GenerationConfig, ModelOutput
 
@@ -29,7 +29,7 @@ from .configuration_chatglm import ChatGLMConfig
 
 # flags required to enable jit fusion kernels
 
-if sys.platform != 'darwin':
+if sys.platform != 'darwin' and not is_torch_npu_available():
     torch._C._jit_set_profiling_mode(False)
     torch._C._jit_set_profiling_executor(False)
     torch._C._jit_override_can_fuse_on_cpu(True)