Equation 14 · Part 2 · Serving a Frontier Model: The KV Cache, Batching, and What a Token Actually Costs
subscript
subscript
What this part means
The lower label selects a particular version, component, or indexed member of the quantity. For example, x₀ and xₜ can be values at different positions.
Its job in the formula
A subscript distinguishes a version, component, step, or member of a quantity. It does not automatically mean multiplication.
Full expression→subscript→Article meaning
The passage around this formula
The other lever is . Standard multi-head attention gives every query head its own key and value heads. Shazeer observed that the key and value projections could be shared across all query heads, cutting the cache by the head count at some quality cost [ 4 ] . Grouped-query attention interpolates: query heads are divided into groups, each sharing one key–value head, and the paper shows the resulting models can be uptrained from existing multi-head checkpoints to reach quality close to the original at speed close to multi-query [ 5 ] .
Learn the underlying idea
A subscript is a label attached below a symbol. It often selects a time step, component, category, or member of a sequence.
Open the illustrated subscripts: which member of a family? guide →
Sources cited in the surrounding passage
- [4] Fast Transformer Decoding: One Write-Head is All You Need ↗
- [5] GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints ↗
These citations provide research context; check each source for the exact claim it supports.