Equation 15 · Part 4 · How Llama's Architecture Actually Works, Generation by Generation
subtraction
subtraction
What this part means
Subtract the following term or group from the preceding one. A leading minus marks a negative quantity.
Its job in the formula
Subtract the following term or group from the preceding one. A leading minus marks a negative quantity.
Full expression→subtraction→Article meaning
The passage around this formula
Multi-head attention gives every query head its own key and value projections. That is expensive at inference time for an autoregressive model, because every generated token requires reading the cached keys and values for every previous token, once per head, from memory — and memory bandwidth, not arithmetic, is usually the bottleneck in decoding. Multi-query attention collapses all query heads onto a single shared key-value pair, cutting that cache to a fraction of its multi-head size at some cost in quality. Ainslie and colleagues proposed the middle path that all three Llama generations actually use: grouped-query attention, in which H query heads are partitioned into G groups, and every…
Learn the underlying idea
Addition combines quantities; subtraction measures the signed difference between them. Parentheses show what is combined before the rest of the expression is evaluated.
Open the illustrated addition and subtraction in an equation guide →
Sources cited in the surrounding passage
These citations provide research context; check each source for the exact claim it supports.