J-KICS

Korean

Digital Library[ Search Result ]

Search : "[ keyword: 모델 병렬화 ]" (2)

An Analysis on Inference Time, Accuracy, Communication, and GPU Memory Usage for Inference Batch of Large Language Models

Changyong Shin Younghun Go Yeonho Yoo Gyeongsik Yang Chuck Yoo

Vol. 49, No. 10, pp. 1377-1385, Oct. 2024

10.7840/kics.2024.49.10.1377

Large Language Model

GPU utilization

communication overhead

Model Parallelism

Tensor parallelism

Comparison and Analysis for the Performance of Deep Learning-Based Time Series Prediction Algorithms According to Increasing Model Size

Youngjoon Choi Daekeun Kim
Vol. 48, No. 1, pp. 123-128, Jan. 2023

10.7840/kics.2023.48.1.123

Time Series Prediction

Model Parallelism