SANTA replaces full value-cache multiply-accumulates with stochastic gather-and-add sampling from the attention distribution to reduce memory bandwidth while preserving an unbiased estimator.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Stochastic Sparse Attention for Memory-Bound Inference
SANTA replaces full value-cache multiply-accumulates with stochastic gather-and-add sampling from the attention distribution to reduce memory bandwidth while preserving an unbiased estimator.