← All parts of this equation

Equation 12 · Part 3 · How AI Memory Systems and the Bandwidth Wall Actually Work

Symbol h

MKV  =  2 n h d e b l,M_{\mathrm{KV}} \;=\; 2 \, n \, h \, d \, e \, b \, l ,
hh

What this part means

h is an input to the expression that computes the quantity on the left.

Its job in the formula

h is an input to the expression that computes the quantity on the left.

The passage around this formula

Hooper and colleagues, working on KV cache compression for very long contexts, state the resulting footprint precisely: for a model with n layers and h attention heads of dimension d , stored using e bytes per element, the KV cache size for batch size b and sequence length l is MKV  =  2 n h d e b lM_{\mathrm{KV}} \;=\; 2 \, n \, h \, d \, e \, b \, l . which grows linearly in both batch size and sequence length, with the leading factor of two accounting for storing both keys and values [ 9 ] . That…

Read this part in the article →

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 →

Sources cited in the surrounding passage

These citations provide research context; check each source for the exact claim it supports.