A co-design of quantization, lookup-table sharing, and analog in-memory circuits lets large KAN recommendation models (39-63MB) scale with 28-41x area growth for 500K-807Kx parameter growth, with 0.11-0.23% accuracy loss in simulation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hardware Acceleration of Kolmogorov-Arnold Network (KAN) in Large-Scale Systems
A co-design of quantization, lookup-table sharing, and analog in-memory circuits lets large KAN recommendation models (39-63MB) scale with 28-41x area growth for 500K-807Kx parameter growth, with 0.11-0.23% accuracy loss in simulation.