Close

Session

Paper: Sparsity and Quantization in ML
Session Chair
Ramakrishnan Kannan
Georgia Institute of Technology
Event TypePaper
TimeThursday, 21 November 20249am - 10am EST
LocationB308
Tags
Algorithms
Artificial Intelligence/Machine Learning
Heterogeneous Computing
Performance Optimization
Registration Categories
TP
Similar Sessions
Machine Learning Applications
Communication Optimization for ML
Efficient Transformers
Presentations
9:00am - 9:30am ESTMIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization by Online Prediction
Authors
Yidong Chen
Chen Zhang
Rongchao Dong
Haoyuan Zhang
Yonghua Zhang
Zhonghua Lu
Jidong Zhai
Algorithms
Artificial Intelligence/Machine Learning
Heterogeneous Computing
Performance Optimization
9:30am - 10:00am ESTLong Exposure: Accelerating Parameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity
Authors
Tuowei Wang
Kun Li
Zixu Hao
Donglin Bai
Ju Ren
Yaoxue Zhang
Ting Cao
Mao Yang
Algorithms
Artificial Intelligence/Machine Learning
Heterogeneous Computing
Performance Optimization