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 …

Large language models (LLMs) have revolutionized natural language processing tasks.
However, their practical deployment is hindered by their immense memory and computation …

Recent advancements in machine learning achieved by Deep Neural Networks (DNNs)
have been significant. While demonstrating high accuracy, DNNs are associated with a …

Large Language Models (LLMs) excel in NLP, but their demands hinder their widespread
deployment. While Quantization-Aware Training (QAT) offers a solution, its extensive …

Modern pre-trained transformers have rapidly advanced the state-of-the-art in machine
learning, but have also grown in parameters and computational complexity, making them …

The recent detection transformer (DETR) has advanced object detection, but its application
on resource-constrained devices requires massive computation and memory resources …

Recent trends in deep learning (DL) imposed hardware accelerators as the most viable
solution for several classes of high-performance computing (HPC) applications such as …

How can we compress language models without sacrificing accuracy? The number of
compression algorithms for language models is rapidly growing to benefit from remarkable …

Weight oscillation is a by-product of quantization-aware training, in which quantized weights
frequently jump between two quantized levels, resulting in training instability and a sub …

While generative modeling has been ubiquitous in natural language processing and
computer vision, its application to image retrieval remains unexplored. In this paper, we …