Home / Current Issue / Paper 1705251
Enhancing Nuclear Medicine Through Innovative AI Models: Integrating Large Language Models and SmoothQuant for Advanced Imaging Precision
Subject area: Science,Engineering and Technology · Area of research: Computer Science Engineering
Abstract
Large language models (LLMs) exhibit superior performance but demand substantial computational and memory resources. Quantization emerges as a viable strategy to alleviate memory requirements and expedite inference. Nonetheless, extant quantization methods encounter challenges in preserving accuracy and ensuring hardware efficiency. This research introduces SmoothQuant, an innovative, training-free, and accuracy-preserving post-training (PTQ) approach, specifically designed to facilitate 8-bit weight and 8-bit activation (W8A8) quantization for LLMs. Leveraging the insight that weights are amenable to quantization while activations pose challenges, SmoothQuant addresses this imbalance by mitigating activation outliers. With the continuous evolution of artificial intelligence (AI) technologies, integrating innovative AI models into the field of nuclear medicine holds immense promise. This research paper explores the synergistic potential of combining Large Language Models (LLMs) and SmoothQuant, a state-of-the-art post-training quantization technique, to achieve advanced imaging precision in nuclear medicine. This is achieved through an offline migration of the quantization complexity from activations to weights, employing a mathematically equivalent transformation. This research presents a turn-key solution that not only optimizes hardware utilization but also contributes to the democratization of LLMs by mitigating associated costs. The study investigates the impact of this integration on data analysis, interpretation, and overall diagnostic accuracy.
Keywords
Nuclear Medicine, Artificial Intelligence, Large Language Models, Imaging Precision, Quantization.
How to cite this paper
@article{1705251,
author = {Sanskar Saxena, Vinod Kumar, Jatin Chopra, Pranjal Gupta, Daamini Batra; Bhaumik Tyagi},
title = {Enhancing Nuclear Medicine Through Innovative AI Models: Integrating Large Language Models and SmoothQuant for Advanced Imaging Precision},
journal = {Iconic Research And Engineering Journals},
year = {2023},
volume = {7},
number = {6},
pages = {1-7},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1705251.pdf},
abstract = {Large language models (LLMs) exhibit superior performance but demand substantial computational and memory resources. Quantization emerges as a viable strategy to alleviate memory requirements and expedite inference. Nonetheless, extant quantization methods encounter challenges in preserving accuracy and ensuring hardware efficiency. This research introduces SmoothQuant, an innovative, training-free, and accuracy-preserving post-training (PTQ) approach, specifically designed to facilitate 8-bit weight and 8-bit activation (W8A8) quantization for LLMs. Leveraging the insight that weights are amenable to quantization while activations pose challenges, SmoothQuant addresses this imbalance by mitigating activation outliers. With the continuous evolution of artificial intelligence (AI) technologies, integrating innovative AI models into the field of nuclear medicine holds immense promise. This research paper explores the synergistic potential of combining Large Language Models (LLMs) and SmoothQuant, a state-of-the-art post-training quantization technique, to achieve advanced imaging precision in nuclear medicine. This is achieved through an offline migration of the quantization complexity from activations to weights, employing a mathematically equivalent transformation. This research presents a turn-key solution that not only optimizes hardware utilization but also contributes to the democratization of LLMs by mitigating associated costs. The study investigates the impact of this integration on data analysis, interpretation, and overall diagnostic accuracy.},
keywords = {Nuclear Medicine, Artificial Intelligence, Large Language Models, Imaging Precision, Quantization.},
month = {December},
}