Saved in:
Bibliographic Details
Main Author: Liguori, Vincenzo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.10896
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917642038673408
author Liguori, Vincenzo
author_facet Liguori, Vincenzo
contents This paper starts with a simple lossless ~1.5:1 compression algorithm for the weights of the Large Language Model (LLM) Llama2 7B [1] that can be implemented in ~200 LUTs in AMD FPGAs, processing over 800 million bfloat16 numbers per second. This framework is then extended to variable precision, variable range, compressed numerical data types that are a user defined super set of both floats and posits [2]. The paper then discusses a simple hardware implementation of such format based on ANS (Asymmetrical Numeral Systems) [3] that acts as a bridge between this flexible data format and a computational engine while, at the same time, achieving bandwidth reduction. An example of a token factory using weight compression and sharing is also given.
format Preprint
id arxiv_https___arxiv_org_abs_2404_10896
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle From a Lossless (~1.5:1) Compression Algorithm for Llama2 7B Weights to Variable Precision, Variable Range, Compressed Numeric Data Types for CNNs and LLMs
Liguori, Vincenzo
Computer Vision and Pattern Recognition
Artificial Intelligence
Hardware Architecture
This paper starts with a simple lossless ~1.5:1 compression algorithm for the weights of the Large Language Model (LLM) Llama2 7B [1] that can be implemented in ~200 LUTs in AMD FPGAs, processing over 800 million bfloat16 numbers per second. This framework is then extended to variable precision, variable range, compressed numerical data types that are a user defined super set of both floats and posits [2]. The paper then discusses a simple hardware implementation of such format based on ANS (Asymmetrical Numeral Systems) [3] that acts as a bridge between this flexible data format and a computational engine while, at the same time, achieving bandwidth reduction. An example of a token factory using weight compression and sharing is also given.
title From a Lossless (~1.5:1) Compression Algorithm for Llama2 7B Weights to Variable Precision, Variable Range, Compressed Numeric Data Types for CNNs and LLMs
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Hardware Architecture
url https://arxiv.org/abs/2404.10896