Set of Indexed Key-Value Pairs

Set of Superscript-Indexed Vectors

Set of Key-Value Pairs

Function of a Sequence of Overlined Variables

Function of a Sequence of Averaged Vectors

Vector Slice Notation for a Sequence Window ($\mathbf{V}_{[i-n+1,i]}$)

Set of Sequential Vectors Notation

Vector Sequence Window Notation

Consider an autoregressive model generating a sequence of tokens one by one. At each step i, the model calculates attention using the query from the current token and the keys and values from all tokens generated so far (from position 1 to i). To optimize this process, the model maintains a growing set of all previously computed key and value vectors. What is the primary computational advantage of this strategy?

State of an Autoregressive Cache

An autoregressive language model with τ parallel computational units (e.g., attention heads) is generating a sequence of tokens. After computing the output for the 3rd token, the model stores the key and value vectors from all tokens processed so far to use in subsequent steps. Which of the following notations correctly represents the complete set of these stored key-value pairs at this specific moment?