aiqbench analysis
This research demonstrates that Transformer architectures can be exactly compiled into generic deep neural networks using only standard NPU operators, eliminating the need for specialized hardware attention units. The study further proves that retaining specific activation-activation product operations significantly reduces computational costs compared to removing them, while also introducing efficient methods for handling clustered queries in multi-agent scenarios. These findings are critical for optimizing model deployment on existing hardware and improving inference efficiency without sacrificing accuracy.
Transformers as Generic Deep Neural Networks: Exact Compilation, the Cost of Removing Activation-Activation Products, and Multi-Agent Attention Clustering
arXiv:2610.28958v1 Announce Type: new Abstract: Transformers are deployed as a special model class. Neural processing units (NPU) add dedicated operators for attention and normalization, and quantization relies on Transformer-specific algorithms. We show the computation does not force this. Every Transformer block, with attention, LayerNorm and a GELU MLP, compiles exactly into a generic deep neural network built from fixed affine maps, routing and the square, sigmoid and inverse square root, plus GELU or its sigmoid approximation. Without activation-activation products, every transform-wise compilation adds at least $N^2$ scalar nonlinear evaluations per head for dense scores. Keeping that one operation type removes this cost; its elementwise form, present on every surveyed NPU, suffices with the sigmoid and inverse square root. For top-$k$ attention with exchangeable tail scores, we prove that exact or conditional-mean tail mass gives an unbiased, minimum-mean-square-error estimate of the attention distribution, while tail drop is conditionally biased. When queries or agents cluster, centroids choose the keys first, reducing the number of computed scores from $N^2$ to $Nk$ per head. On DeiT-Tiny, MambaIRv2-Light and Pythia-70M the compiled models match their references with all keys, standard post-training quantization applies, and the exact tail-mass estimate beats tail dropping with half as many keys on DeiT-Tiny and, for $k\le8$, on Pythia-70M.
Abstract:Transformers are deployed as a special model class. Neural processing units (NPU) add dedicated operators for attention and normalization, and quantization relies on Transformer-specific algorithms. We show the computation does not force this. Every Transformer block, with attention, LayerNorm and a GELU MLP, compiles exactly into a generic deep neural network built from fixed affine maps, routing and the square, sigmoid and inverse square root, plus GELU or its sigmoid approximation. Without activation-activation products, every transform-wise compilation adds at least $N^2$ scalar nonlinear evaluations per head for dense scores. Keeping that one operation type removes this cost; its elementwise form, present on every surveyed NPU, suffices with the sigmoid and inverse square root. For top-$k$ attention with exchangeable tail scores, we prove that exact or conditional-mean tail mass gives an unbiased, minimum-mean-square-error estimate of the attention distribution, while tail drop is conditionally biased. When queries or agents cluster, centroids choose the keys first, reducing the number of computed scores from $N^2$ to $Nk$ per head. On DeiT-Tiny, MambaIRv2-Light and Pythia-70M the compiled models match their references with all keys, standard post-training quantization applies, and the exact tail-mass estimate beats tail dropping with half as many keys on DeiT-Tiny and, for $k\le8$, on Pythia-70M.
36 pages, 6 tables and 2 figures in the main text, 8 supplementary tables. Code: this https URL
Machine Learning (cs.LG); Multiagent Systems (cs.MA)
arXiv:2610.28958 [cs.LG]
(or arXiv:2610.28958v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.28958 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 318 words