← All parts of this equation

Equation 4 · Part 2 · The Physical Economics of Inference: Bandwidth, Energy, and the Limits of a Datacenter

Symbol L

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

What this part means

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

Its job in the formula

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

The passage around this formula

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 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 →

The article lists its research sources here.