optimum/exporters/ipex/modeling_utils.py [704:755]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    position_embeddings = (cos.unsqueeze(1), sin.unsqueeze(1))

    if past_key_values is None:
        attention_mask = self._update_causal_mask(
            attention_mask, inputs_embeds, cache_position, past_key_values, output_attentions
        )

    # decoder layers
    all_hidden_states = () if output_hidden_states else None
    all_self_attns = () if output_attentions else None

    for decoder_layer in self.layers[: self.config.num_hidden_layers]:
        if output_hidden_states:
            all_hidden_states += (hidden_states,)

        layer_outputs = decoder_layer(
            hidden_states,
            attention_mask=attention_mask,
            position_ids=position_ids,
            past_key_value=past_key_values,
            output_attentions=output_attentions,
            use_cache=use_cache,
            cache_position=cache_position,
            position_embeddings=position_embeddings,
            past_key_values_length=past_key_values_length,
            max_input_lens=max_input_lens,
            query_max_len=seq_length,
            **kwargs,
        )

        hidden_states = layer_outputs[0]

        if output_attentions:
            all_self_attns += (layer_outputs[1],)

    hidden_states = self.norm(hidden_states)

    if hidden_states.shape[0] != batch_size * seq_length:
        (hidden_states_copy.view(-1, hidden_states.shape[-1]))[attention_mask.view(-1) != 0] = hidden_states
        hidden_states = hidden_states_copy
    hidden_states = hidden_states.view(batch_size, -1, hidden_states.shape[-1])
    # add hidden states from the last decoder layer
    if output_hidden_states:
        all_hidden_states += (hidden_states,)

    output = BaseModelOutputWithPast(
        last_hidden_state=hidden_states,
        past_key_values=past_key_values if use_cache else None,
        hidden_states=all_hidden_states,
        attentions=all_self_attns,
    )
    return output if return_dict else output.to_tuple()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/exporters/ipex/modeling_utils.py [818:868]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        position_embeddings = (cos.unsqueeze(1), sin.unsqueeze(1))
    if past_key_values is None:
        attention_mask = self._update_causal_mask(
            attention_mask, inputs_embeds, cache_position, past_key_values, output_attentions
        )

    # decoder layers
    all_hidden_states = () if output_hidden_states else None
    all_self_attns = () if output_attentions else None

    for decoder_layer in self.layers[: self.config.num_hidden_layers]:
        if output_hidden_states:
            all_hidden_states += (hidden_states,)

        layer_outputs = decoder_layer(
            hidden_states,
            attention_mask=attention_mask,
            position_ids=position_ids,
            past_key_value=past_key_values,
            output_attentions=output_attentions,
            use_cache=use_cache,
            cache_position=cache_position,
            position_embeddings=position_embeddings,
            past_key_values_length=past_key_values_length,
            max_input_lens=max_input_lens,
            query_max_len=seq_length,
            **kwargs,
        )

        hidden_states = layer_outputs[0]

        if output_attentions:
            all_self_attns += (layer_outputs[1],)

    hidden_states = self.norm(hidden_states)

    if hidden_states.shape[0] != batch_size * seq_length:
        (hidden_states_copy.view(-1, hidden_states.shape[-1]))[attention_mask.view(-1) != 0] = hidden_states
        hidden_states = hidden_states_copy
    hidden_states = hidden_states.view(batch_size, -1, hidden_states.shape[-1])
    # add hidden states from the last decoder layer
    if output_hidden_states:
        all_hidden_states += (hidden_states,)

    output = BaseModelOutputWithPast(
        last_hidden_state=hidden_states,
        past_key_values=past_key_values if use_cache else None,
        hidden_states=all_hidden_states,
        attentions=all_self_attns,
    )
    return output if return_dict else output.to_tuple()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -