optimum/onnxruntime/modeling_seq2seq.py [569:596]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            if not self.use_past_in_outputs:
                out_past_key_values = None
            elif not self.use_past_in_inputs or use_merged_no_cache or self.no_cross_attention_cache:
                out_past_key_values = tuple(
                    out_past_key_values[i : i + self.num_pkv] for i in range(0, len(out_past_key_values), self.num_pkv)
                )
            else:
                if self.use_legacy_outputs is True:
                    msg = (
                        "For the decoder with past, using ONNX models outputting cross attention past key values"
                        " is deprecated and the support will be removed in optimum 2.0. We recommend exporting again the model"
                        " with optimum>=1.7.3."
                    )
                    warn_once(logger, msg=msg)
                    out_past_key_values = tuple(
                        out_past_key_values[i : i + self.num_pkv]
                        for i in range(0, len(out_past_key_values), self.num_pkv)
                    )
                # grab the cross attention key/values from the inputs
                elif self.num_pkv == 2:
                    out_past_key_values = tuple(
                        out_past_key_values[i : i + self.num_pkv]
                        + past_key_values[2 * i + 2 : 2 * i + 2 + self.num_pkv]
                        for i in range(0, len(out_past_key_values), self.num_pkv)
                    )
                elif self.num_pkv == 4:
                    # despite num_pkv being 4, we did not bind the cross-attention output
                    out_past_key_values = tuple(
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/onnxruntime/modeling_seq2seq.py [620:646]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            if not self.use_past_in_outputs:
                out_past_key_values = None
            elif not self.use_past_in_inputs or use_merged_no_cache or self.no_cross_attention_cache:
                out_past_key_values = tuple(
                    out_past_key_values[i : i + self.num_pkv] for i in range(0, len(out_past_key_values), self.num_pkv)
                )
            else:
                if self.use_legacy_outputs is True:
                    msg = (
                        "For the decoder with past, using ONNX models outputting cross attention past key values"
                        " is deprecated and the support will be removed in optimum 2.0. We recommend exporting again the model"
                        " with optimum>=1.7.3."
                    )
                    warn_once(logger, msg=msg)
                    out_past_key_values = tuple(
                        out_past_key_values[i : i + self.num_pkv]
                        for i in range(0, len(out_past_key_values), self.num_pkv)
                    )
                # grab the cross attention key/values from the inputs
                elif self.num_pkv == 2:
                    out_past_key_values = tuple(
                        out_past_key_values[i : i + self.num_pkv]
                        + past_key_values[2 * i + 2 : 2 * i + 2 + self.num_pkv]
                        for i in range(0, len(out_past_key_values), self.num_pkv)
                    )
                elif self.num_pkv == 4:
                    out_past_key_values = tuple(
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -