Equation 13 · Part 1 · AI Memory Systems and the Bandwidth Wall in 2035: Scenarios, Signals, and Falsifiable Predictions
Symbol M_KV
What this part means
V is part of the quantity the equation computes from the expression on the right.
Its job in the formula
V is part of the quantity the equation computes from the expression on the right.
Full expression→Symbol M_KV→Article meaning
The passage around this formula
Fact. The memory a transformer must hold for one in-flight generation — its key-value cache — grows linearly in exactly the variables that make serving expensive: sequence length and batch size. For a model with L layers, key-value heads, head dimension , sequence length S , batch size B , and p bytes stored per element, the cache occupies approximately . bytes, the leading factor of two accounting for keys and values together. That equation is worth writing out because it exposes the one real lever every mitigation below actually pulls: none of them escapes linear growth in S and B . Each instead shrinks one of the other factors — most consequentially…
Learn the underlying idea
A subscript is a label attached below a symbol. It often selects a time step, component, category, or member of a sequence.
Open the illustrated subscripts: which member of a family? guide →
See this notation across published equations →
Sources cited in the article section
- [15] DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model ↗
- [14] Efficient Streaming Language Models with Attention Sinks ↗
- [16] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models ↗
These citations provide research context; check each source for the exact claim it supports.