optimum/habana/transformers/models/llama/modeling_llama.py [720:778]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if use_flash_attention and FusedSDPA is not None:
            attn_weights = None
            if q_len == 1:
                # next token
                attn_output = fused_scaled_dot_product_attention(
                    query_states,
                    key_states,
                    value_states,
                    attention_mask,
                    0.0,
                    False,
                    None,
                    "None",
                    False,
                    None,
                    "None",
                )
            else:
                # first token
                softmax_mode = "fast" if flash_attention_fast_softmax else "None"
                if flash_attention_causal_mask:
                    # causal masking on first token requires inputs to be of the same length
                    attn_output = fused_scaled_dot_product_attention(
                        query_states,
                        key_states,
                        value_states,
                        None,
                        0.0,
                        True,
                        None,
                        softmax_mode,
                        flash_attention_recompute,
                        valid_sequence_lengths,
                        "left",
                    )
                else:
                    attn_output = fused_scaled_dot_product_attention(
                        query_states,
                        key_states,
                        value_states,
                        attention_mask,
                        0.0,
                        False,
                        None,
                        softmax_mode,
                        flash_attention_recompute,
                        None,
                        "None",
                    )

        else:
            attn_output, attn_weights = gaudi_eager_attention_forward(
                self,
                query_states,
                key_states,
                value_states,
                attention_mask,
                dropout=0.0 if not self.training else self.attention_dropout,
                scaling=self.scaling,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/habana/transformers/models/qwen2/modeling_qwen2.py [488:545]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if use_flash_attention and FusedSDPA is not None:
            attn_weights = None
            if q_len == 1:
                # next token
                attn_output = fused_scaled_dot_product_attention(
                    query_states,
                    key_states,
                    value_states,
                    attention_mask,
                    0.0,
                    False,
                    None,
                    "None",
                    False,
                    None,
                    "None",
                )
            else:
                # first token
                softmax_mode = "fast" if flash_attention_fast_softmax else "None"
                if flash_attention_causal_mask:
                    attn_output = fused_scaled_dot_product_attention(
                        query_states,
                        key_states,
                        value_states,
                        None,
                        0.0,
                        True,
                        None,
                        softmax_mode,
                        flash_attention_recompute,
                        valid_sequence_lengths,
                        "left",
                    )
                else:
                    attn_output = fused_scaled_dot_product_attention(
                        query_states,
                        key_states,
                        value_states,
                        attention_mask,
                        0.0,
                        False,
                        None,
                        softmax_mode,
                        flash_attention_recompute,
                        None,
                        "None",
                    )

        else:
            attn_output, attn_weights = gaudi_eager_attention_forward(
                self,
                query_states,
                key_states,
                value_states,
                attention_mask,
                dropout=0.0 if not self.training else self.attention_dropout,
                scaling=self.scaling,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -