optimum/onnxruntime/modeling_ort.py [1691:1721]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
    )
    def forward(
        self,
        input_values: Optional[Union[torch.Tensor, np.ndarray]] = None,
        *,
        return_dict: bool = True,
        **kwargs,
    ):
        # Warn about any unexpected kwargs using the helper method
        self._warn_on_unhandled_inputs(kwargs)

        use_torch = isinstance(input_values, torch.Tensor)
        self.raise_on_numpy_input_io_binding(use_torch)

        model_inputs = {
            "input_values": input_values,
        }

        if self.use_io_binding:
            output_shapes, output_buffers = self._prepare_io_binding(model_inputs)

            # run inference with binding & synchronize in case of multiple CUDA streams
            if self.device.type == "cpu":
                self.session.run_with_iobinding(self._io_binding)
            else:
                self._io_binding.synchronize_inputs()
                self.session.run_with_iobinding(self._io_binding)
                self._io_binding.synchronize_outputs()

            logits = output_buffers["logits"].view(output_shapes["logits"])
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/onnxruntime/modeling_ort.py [1780:1810]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
    )
    def forward(
        self,
        input_values: Optional[Union[torch.Tensor, np.ndarray]] = None,
        *,
        return_dict: bool = True,
        **kwargs,
    ):
        # Warn about any unexpected kwargs using the helper method
        self._warn_on_unhandled_inputs(kwargs)

        use_torch = isinstance(input_values, torch.Tensor)
        self.raise_on_numpy_input_io_binding(use_torch)

        model_inputs = {
            "input_values": input_values,
        }

        if self.use_io_binding:
            output_shapes, output_buffers = self._prepare_io_binding(model_inputs)

            # run inference with binding & synchronize in case of multiple CUDA streams
            if self.device.type == "cpu":
                self.session.run_with_iobinding(self._io_binding)
            else:
                self._io_binding.synchronize_inputs()
                self.session.run_with_iobinding(self._io_binding)
                self._io_binding.synchronize_outputs()

            logits = output_buffers["logits"].view(output_shapes["logits"])
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -