P011Filed

Attention Mechanism Compression via Ternary Quantization

The transformer attention mechanism — rebuilt for three values.

AU Application
2023900011
Filing Date
5 March 2023
Index Number
P011
Figures
15 figures
Batch / Category
Core 1

Explore the Vision

Discover this technology through five complementary perspectives — from technical architecture to partnership outcomes. Each layer reveals a different aspect of how this innovation creates value.

The transformer attention mechanism — rebuilt for three values.

What It IS

Technical Vision

The architectural essence — what makes this technology work

The multi-headed attention mechanism of a large language model rendered as a crown of parallel beams, each beam now carrying ternary queries, keys, and values. Where attention scores once demanded expensive matrix multiplications, compare-and-select operations produce the same focus in a fraction of the energy.

1/5
Explore the buyer's journey across 5 perspectives

Abstract

Methods for compressing transformer attention mechanisms into ternary representation while maintaining semantic information and model expressiveness.

Visual Essence

The multi-headed attention mechanism of a large language model rendered as a crown of parallel beams, each beam now carrying ternary queries, keys, and values. Where attention scores once demanded expensive matrix multiplications, compare-and-select operations produce the same focus in a fraction of the energy.

Visual Family:silicon-awakening

Technology Domains

Related Patents

From the silicon-awakening visual family