TripleOptim: A Comprehensive Optimization Framework for GPTQ Quantization Inference on Heterogeneous Platforms.

Saved in:
Bibliographic Details
Title: TripleOptim: A Comprehensive Optimization Framework for GPTQ Quantization Inference on Heterogeneous Platforms.
Authors: Wei Wang1, wei_wang_cn@126.com, Lin Han1, strollerlin@163.com, Jiehan Zhou2, jiehan.zhou@sdust.edu.cn, Jinling Yu2, jlyu0201@163.com, Jingming Xie3, jing_ming_xie@163.com, Chaowei Kong3, chaoweiKong@126.com, Zhenqi Gao4, zhenqigao@126.com
Source: KSII Transactions on Internet & Information Systems; May2025, Vol. 19 Issue 5, p1441-1458, 18p
Database: Applied Science & Technology Source
Description
ISSN:19767277
DOI:10.3837/tiis.2025.05.003