Recent years have seen a phenomenal rise in the performance and applications of
transformer neural networks. The family of transformer networks, including Bidirectional …

Deep learning (DL) has recently changed the development of intelligent systems and is
widely adopted in many real-life applications. Despite their various benefits and potentials …

Several post-training quantization methods have been applied to large language models
(LLMs), and have been shown to perform well down to 8-bits. We find that these methods …

This paper explores network binarization, a radical form of quantization, compressing model
weights to a single bit, specifically for Large Language Models (LLMs) compression. Due to …

Network binarization emerges as one of the most promising compression approaches
offering extraordinary computation and memory savings by minimizing the bit-width …

Abstract Model binarization can significantly compress model size, reduce energy
consumption, and accelerate inference through efficient bit-wise operations. Although …

With the increasing popularity and the increasing size of vision transformers (ViTs), there
has been an increasing interest in making them more efficient and less computationally …

Matrix multiplication (MatMul) typically dominates the overall computational cost of large
language models (LLMs). This cost only grows as LLMs scale to larger embedding …

Large language models (LLMs) have significantly advanced the field of natural language
processing, while the expensive memory and computation consumption impede their …

Abstract Vision Transformers (ViTs) have shown impressive performance and have become
a unified backbone for multiple vision tasks. However, both the attention mechanism and …