optimum/habana/transformers/models/deepseek_v3/modeling_deepseek_v3.py [657:708]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if idx is not None:
            prev.index_copy_(dim, idx - 1, cur)
            return prev
        else:
            return torch.cat((prev, cur), dim=dim)

    def get_shape(self):
        if self.cache is None:
            return None
        return self.cache.shape

    def forward(self, cur, dim, idx):
        return self.update(self.cache, cur, dim, idx, self.inp_seq_len)


# hpu specific fused op. wrapped in a class as functional apis not supported for quantization
class ModuleFusedSDPA(torch.nn.Module):
    def __init__(self, fusedSDPA, scale, attention_dropout, enable_recompute, flash_attention_fp8):
        super().__init__()
        self._hpu_kernel_fsdpa = fusedSDPA
        self.scale = scale
        self.attention_dropout = attention_dropout
        self.enable_recompute = enable_recompute
        self.flash_attention_fp8 = flash_attention_fp8

    def forward(
        self,
        query,
        key,
        value,
        attn_mask,
        dropout_p,
        is_casual,
        scale,
        softmax_mode,
        recompute_mode,
        valid_sequence_lengths,
        padding_side="left",
    ):
        return self._hpu_kernel_fsdpa.apply(
            query,
            key,
            value,
            attn_mask,
            dropout_p,
            is_casual,
            scale,
            softmax_mode,
            recompute_mode,
            valid_sequence_lengths,
            padding_side,
        )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/habana/transformers/models/qwen2_moe/modeling_qwen2_moe.py [206:257]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if idx is not None:
            prev.index_copy_(dim, idx - 1, cur)
            return prev
        else:
            return torch.cat((prev, cur), dim=dim)

    def get_shape(self):
        if self.cache is None:
            return None
        return self.cache.shape

    def forward(self, cur, dim, idx):
        return self.update(self.cache, cur, dim, idx, self.inp_seq_len)


#  FusedScaledDotProductAttention
class ModuleFusedSDPA(torch.nn.Module):
    def __init__(self, fusedSDPA, scale, attention_dropout, enable_recompute, flash_attention_fp8):
        super().__init__()
        self._hpu_kernel_fsdpa = fusedSDPA
        self.scale = scale
        self.attention_dropout = attention_dropout
        self.enable_recompute = enable_recompute
        self.flash_attention_fp8 = flash_attention_fp8

    def forward(
        self,
        query,
        key,
        value,
        attn_mask,
        dropout_p,
        is_casual,
        scale,
        softmax_mode,
        recompute_mode,
        valid_sequence_lengths,
        padding_side="left",
    ):
        return self._hpu_kernel_fsdpa.apply(
            query,
            key,
            value,
            attn_mask,
            dropout_p,
            is_casual,
            scale,
            softmax_mode,
            recompute_mode,
            valid_sequence_lengths,
            padding_side,
        )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -