optimum/onnxruntime/modeling_ort.py [1288:1327]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
    )
    def forward(
        self,
        pixel_values: Union[torch.Tensor, np.ndarray],
        *,
        return_dict: bool = True,
        **kwargs,
    ):
        # Warn about any unexpected kwargs using the helper method
        self._warn_on_unhandled_inputs(kwargs)

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

        model_inputs = {
            "pixel_values": pixel_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"])
        else:
            onnx_inputs = self._prepare_onnx_inputs(use_torch, model_inputs)
            onnx_outputs = self.model.run(None, onnx_inputs)
            model_outputs = self._prepare_onnx_outputs(use_torch, onnx_outputs)

            logits = model_outputs["logits"]

        if not return_dict:
            return (logits,)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/onnxruntime/modeling_ort.py [1386:1425]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
    )
    def forward(
        self,
        pixel_values: Union[torch.Tensor, np.ndarray],
        *,
        return_dict: bool = True,
        **kwargs,
    ):
        # Warn about any unexpected kwargs using the helper method
        self._warn_on_unhandled_inputs(kwargs)

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

        model_inputs = {
            "pixel_values": pixel_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"])
        else:
            onnx_inputs = self._prepare_onnx_inputs(use_torch, model_inputs)
            onnx_outputs = self.model.run(None, onnx_inputs)
            model_outputs = self._prepare_onnx_outputs(use_torch, onnx_outputs)

            logits = model_outputs["logits"]

        if not return_dict:
            return (logits,)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -