Equation 11 · Part 1 · The Physical Economics of Inference: Bandwidth, Energy, and the Limits of a Datacenter
Symbol e
What this part means
the average energy per byte moved off-chip, energy per token is roughly e B/b — the weight traffic divided across the batch, plus each request’s own cache traffic.
Its job in the formula
e is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.
Full expression→Symbol e→Article meaning
Where the article explains it
If e is the average energy per byte moved off-chip, energy per token is roughly e B/b — the weight traffic divided across the batch, plus each request’s own cache traffic.
The passage around this formula
The energy version of the same expression is more useful still. If e is the average energy per byte moved off-chip, energy per token is roughly e B/b — the weight traffic divided across the batch, plus each request’s own cache traffic. Batching therefore improves energy per token steeply at first and then asymptotically, converging on the irreducible per-request cache cost. That asymptote is the floor referred to throughout this article, and only cache-reduction techniques lower it.
Learn the underlying idea
A variable is a named place for a value. Its letter is a local label: x can mean position in one formula and a data point in another.
Open the illustrated variables: a letter stands for a value guide →
See this notation across published equations →
The article lists its research sources here.