InMemQK: A Product Quantization Based MatMul Module for Compute-in-Memory Attention Macro

InMemQK: A Product Quantization Based MatMul Module for Compute-in-Memory Attention Macro

Large Language Models (LLMs), based on transformer architecture, have demonstrated remarkable capabilities in natural language processing tasks, enabling machines to generate human-like text and engage in meaningful dialogues. However, the exponential increase in model parameters has led to limitati...

Full description

Saved in:
Bibliographic Details
Main Authors: Pengcheng Feng, Yihao Chen, Jinke Yu, Hao Yue, Zhelong Jiang, Yi Xiao, Wan’ang Xiao, Huaxiang Lu, Gang Chen
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Applied Sciences
Subjects:
neural network
compute in memory
transformer
time domain
non-volatile memory
Online Access:https://www.mdpi.com/2076-3417/14/23/11198
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://www.mdpi.com/2076-3417/14/23/11198

Similar Items