optimum/habana/transformers/models/gemma2/modeling_gemma2.py [730:786]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if self.gradient_checkpointing and self.training and use_cache:
            logger.warning_once(
                "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`."
            )
            use_cache = False

        if inputs_embeds is None:
            inputs_embeds = self.embed_tokens(input_ids)

        ignore_cache_position = True  # Ignoring cache position for HPU
        use_new_cache = False  # Ignoring new Cache path for HPU

        past_seen_tokens = 0

        if past_key_values is not None and use_cache:  # kept for BC (cache positions)
            if reuse_cache:
                if isinstance(past_key_values[0][0], torch.Tensor):
                    past_seen_tokens = past_key_values[0][0].shape[2]
                else:
                    past_seen_tokens = past_key_values[0][0][2]
            else:
                if use_new_cache:
                    if not isinstance(past_key_values, StaticCache):
                        past_key_values = DynamicCache.from_legacy_cache(past_key_values)
                    past_seen_tokens = past_key_values.get_seq_length()
                else:
                    past_seen_tokens = past_key_values[0][0].shape[2]

        if ignore_cache_position is False:
            if cache_position is None:
                past_seen_tokens = past_key_values.get_seq_length() if past_key_values is not None else 0
                cache_position = torch.arange(
                    past_seen_tokens, past_seen_tokens + inputs_embeds.shape[1], device=inputs_embeds.device
                )
            if position_ids is None and cache_position:
                position_ids = cache_position.unsqueeze(0)
        else:
            if position_ids is None:
                position_ids = torch.arange(
                    past_seen_tokens, seq_length + past_seen_tokens, dtype=torch.long, device=inputs_embeds.device
                )
                position_ids = position_ids.unsqueeze(0)
            cache_position = None

        # HPU specific mask generation
        if ignore_cache_position:
            causal_mask = _gaudi_prepare_4d_causal_attention_mask(
                attention_mask,
                input_ids.shape if input_ids is not None else (batch_size, seq_length),
                inputs_embeds,
                past_seen_tokens,
            )
        else:
            causal_mask = self._update_causal_mask(attention_mask, inputs_embeds, cache_position, past_seen_tokens)

        # embed positions
        hidden_states = inputs_embeds
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/habana/transformers/models/qwen2/modeling_qwen2.py [797:853]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if self.gradient_checkpointing and self.training and use_cache:
            logger.warning_once(
                "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`."
            )
            use_cache = False

        if inputs_embeds is None:
            inputs_embeds = self.embed_tokens(input_ids)

        ignore_cache_position = True  # Ignoring cache position for HPU
        use_new_cache = False  # Ignoring new Cache path for HPU

        past_seen_tokens = 0

        if past_key_values is not None and use_cache:  # kept for BC (cache positions)
            if reuse_cache:
                if isinstance(past_key_values[0][0], torch.Tensor):
                    past_seen_tokens = past_key_values[0][0].shape[2]
                else:
                    past_seen_tokens = past_key_values[0][0][2]
            else:
                if use_new_cache:
                    if not isinstance(past_key_values, StaticCache):
                        past_key_values = DynamicCache.from_legacy_cache(past_key_values)
                    past_seen_tokens = past_key_values.get_seq_length()
                else:
                    past_seen_tokens = past_key_values[0][0].shape[2]

        if ignore_cache_position is False:
            if cache_position is None:
                past_seen_tokens = past_key_values.get_seq_length() if past_key_values is not None else 0
                cache_position = torch.arange(
                    past_seen_tokens, past_seen_tokens + inputs_embeds.shape[1], device=inputs_embeds.device
                )
            if position_ids is None and cache_position:
                position_ids = cache_position.unsqueeze(0)
        else:
            if position_ids is None:
                position_ids = torch.arange(
                    past_seen_tokens, seq_length + past_seen_tokens, dtype=torch.long, device=inputs_embeds.device
                )
                position_ids = position_ids.unsqueeze(0)
            cache_position = None

        # HPU specific mask generation
        if ignore_cache_position:
            causal_mask = _gaudi_prepare_4d_causal_attention_mask(
                attention_mask,
                input_ids.shape if input_ids is not None else (batch_size, seq_length),
                inputs_embeds,
                past_seen_tokens,
            )
        else:
            causal_mask = self._update_causal_mask(attention_mask, inputs_embeds, cache_position, past_seen_tokens)

        # embed positions
        hidden_states = inputs_embeds
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -