mesh_tensorflow/transformer/transformer.py [1146:1167]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        length_dim=length_dim,
        variable_dtype=variable_dtype,
        mode="first_part",
        position=length_range,
        position_is_default=True,
        new_states=[],
        initial_position=initial_position,
        sequence_id=sequence_id,
        encoder_output=encoder_output,
        encoder_sequence_id=encoder_sequence_id,
        constant_states=[],
        shared_params=shared_params,
        encoder_layer_outputs=encoder_layer_outputs,
        write_priority=write_priority,
        read_priority=read_priority,
        inputs=inputs,
        encoder_inputs=encoder_inputs)

    shifted_inputs = autoregressive_inputs(inputs)
    with tf.variable_scope(self.name):
      logits = self._call_internal(context_first_part, shifted_inputs)
    del logits
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



mesh_tensorflow/transformer/transformer.py [1321:1342]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        length_dim=length_dim,
        variable_dtype=variable_dtype,
        mode="first_part",
        position=length_range,
        position_is_default=True,
        new_states=[],
        initial_position=initial_position,
        sequence_id=sequence_id,
        encoder_output=encoder_output,
        encoder_sequence_id=encoder_sequence_id,
        constant_states=[],
        shared_params=shared_params,
        encoder_layer_outputs=encoder_layer_outputs,
        write_priority=write_priority,
        read_priority=read_priority,
        inputs=inputs,
        encoder_inputs=encoder_inputs)

    shifted_inputs = autoregressive_inputs(inputs)
    with tf.variable_scope(self.name):
      logits = self._call_internal(context_first_part, shifted_inputs)
    del logits
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -