Published equation contexts
Why this formula appears here
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 . 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 representative guide
Symbol L
L is an input to the expression that computes the quantity on the left.
Read this term in its guide →Symbol n_kv
v is an input to the expression that computes the quantity on the left.
Read this term in its guide →Symbol d_head
ead is an input to the expression that computes the quantity on the left.
Read this term in its guide →Symbol p
p is an input to the expression that computes the quantity on the left.
Read this term in its guide →How to interpret it
Read it with the definitions, units, and assumptions supplied by the article.
Published contexts (1)
A symbol can carry a different meaning in another article. Each occurrence keeps its own guide and term definitions.
Equation 4 · Foundation Models
The Physical Economics of Inference: Bandwidth, Energy, and the Limits of a Datacenter
This equation states an equality: the expressions on both sides have the same value under the article’s assumptions.
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 . 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