Method forward_nested

model/layers/block.py:209–247

x_list contains a list of tensors to nest together and run

(self, x_list: List[Tensor])

class NestedTensorBlock(Block):
    def forward_nested(self, x_list: List[Tensor]) -> List[Tensor]:
        """
        x_list contains a list of tensors to nest together and run
        """
        assert isinstance(self.attn, MemEffAttention)

        if self.training and self.sample_drop_ratio > 0.0:

            def attn_residual_func(x: Tensor, attn_bias=None) -> Tensor:
                return self.attn(self.norm1(x), attn_bias=attn_bias)

            def ffn_residual_func(x: Tensor, attn_bias=None) -> Tensor:
                return self.mlp(self.norm2(x))

            x_list = drop_add_residual_stochastic_depth_list(
                x_list,
                residual_func=attn_residual_func,
                sample_drop_ratio=self.sample_drop_ratio,
                scaling_vector=self.ls1.gamma if isinstance(self.ls1, LayerScale) else None,
            )
            x_list = drop_add_residual_stochastic_depth_list(
                x_list,
                residual_func=ffn_residual_func,
                sample_drop_ratio=self.sample_drop_ratio,
                scaling_vector=self.ls2.gamma if isinstance(self.ls1, LayerScale) else None,
            )
            return x_list
        else:

            def attn_residual_func(x: Tensor, attn_bias=None) -> Tensor:
                return self.ls1(self.attn(self.norm1(x), attn_bias=attn_bias))

            def ffn_residual_func(x: Tensor, attn_bias=None) -> Tensor:
                return self.ls2(self.mlp(self.norm2(x)))

            attn_bias, x = get_attn_bias_and_cat(x_list)
            x = x + attn_residual_func(x, attn_bias=attn_bias)
            x = x + ffn_residual_func(x)
            return attn_bias.split(x)

    def forward(self, x_or_x_list):
        if isinstance(x_or_x_list, Tensor):