← Back to article

Equation 4 · The Physical Economics of Inference: Bandwidth, Energy, and the Limits of a Datacenter

What does this equation mean?

Mkv=2 L nkv dhead s p,M_{\mathrm{kv}} = 2\,L\,n_{\mathrm{kv}}\,d_{\mathrm{head}}\,s\,p,

Read the formula alongside the article passage below. Each part has a deeper page with its role in the equation, the supporting passage and nearby citations.

Inputs and operations2Ln_kvd_headsp
Result or conditionM_kv
How to read the two sides of this formula. Follow the article passage for the meaning of each quantity.

This equation states an equality: the expressions on both sides have the same value under the article’s assumptions. Read the equation part by part below; each part has a contextual explanation and a link to its mathematical background.

Read it piece by piece

MkvM_{\mathrm{kv}}

Symbol M_kv

the per-request cache traffic.

Understand this part →

LL

Symbol L

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

Understand this part →

nkvn_{\mathrm{kv}}

Symbol n_kv

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

Understand this part →

dheadd_{\mathrm{head}}

Symbol d_head

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

Understand this part →

ss

Symbol s

therefore approximately.

Understand this part →

pp

Symbol p

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

Understand this part →

=

=

The expressions on both sides represent the same quantity under the stated assumptions.

Understand this part →

See an illustrated explanation →
subscript

subscript

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.

Understand this part →

How to interpret it

Read it with the definitions, units, and assumptions supplied by the article.

What the article says around this equation

Take a dense model with N parameters served at p bytes per parameter. The weight traffic per decoding step is Np , incurred once per step regardless of how many requests share it. The per-request cache traffic is Mkv=2 L nkv dhead s pM_{\mathrm{kv}} = 2\,L\,n_{\mathrm{kv}}\,d_{\mathrm{head}}\,s\,p. read in full every step for every active request. Total bytes moved per step across a batch of b requests at sequence length s is therefore approximately

Read the equation in its article →

For background, read the article’s source list.

Return to The Physical Economics of Inference: Bandwidth, Energy, and the Limits of a Datacenter

See this formula across 1 published context →

Browse the mathematical compendium →