Method update

src/transformers/src/transformers/cache_utils.py:34–58

Updates the cache with the new `key_states` and `value_states` for the layer `layer_idx`. Parameters: key_states (`torch.Tensor`): The new key states to cache. value_states (`torch.Tensor`): The new value states to cache.

(
        self,
        key_states: torch.Tensor,
        value_states: torch.Tensor,
        layer_idx: int,
        cache_kwargs: Optional[Dict[str, Any]] = None,
    )

        super().__init__()

    def update(
        self,
        key_states: torch.Tensor,
        value_states: torch.Tensor,
        layer_idx: int,
        cache_kwargs: Optional[Dict[str, Any]] = None,
    ) -> Tuple[torch.Tensor, torch.Tensor]:
        """
        Updates the cache with the new `key_states` and `value_states` for the layer `layer_idx`.

        Parameters:
            key_states (`torch.Tensor`):
                The new key states to cache.
            value_states (`torch.Tensor`):
                The new value states to cache.
            layer_idx (`int`):
                The index of the layer to cache the states for.
            cache_kwargs (`Dict[str, Any]`, `optional`):
                Additional arguments for the cache subclass. These are specific to each subclass and allow new types of
                cache to be created.

        Return:
            A tuple containing the updated key and value states.
        """
        raise NotImplementedError("Make sure to implement `update` in a subclass.")

    def get_seq_length(self, layer_idx: Optional[int] = 0) -> int:
        """Returns the sequence length of the cached states. A layer index can be optionally passed."""