Jul 2026
ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour
ATLAS is a training-free framework that automates this search by treating each layer's approximation setting as a multi-objective optimization over latency and accuracy, and works across encoder-only, decoder-only, and vision Transformers, complementing parallel work on packing and matrix multiplication.
Jianhang Xie, Sicheng Tan, V. Boddeti et al.
· arXiv.org · 1 citation