PF-261116.000001 · Nov 16, 2026
Accepted
What Costs Rows in Small EZKL Transformer Circuits, and What It Costs in Quantized Quality
Nissan Pow
Published accounts argue that nonlinear operations can dominate zero-knowledge (ZK) inference cost, while matrix products can be relatively cheap. We measure how EZKL 23.0.5 allocates rows and advice columns for small causal transformers and what small jointly trained and compiled models cost in…