SC24 Home
Close

Session

Paper: GPU Optimizations for ML
Session Chair
Dong Li
University of California, Merced
Event TypePaper
TimeWednesday, 20 November 202410:30am - 12pm EST
LocationB308
Tags
Accelerators
Artificial Intelligence/Machine Learning
Cloud Computing
Distributed Computing
Heterogeneous Computing
Performance Optimization
Registration Categories
TP
Similar Sessions
Communication Optimization for ML
Machine Learning Applications
Principles and Practice of High Performance Deep/Machine Learning Training and Inference
Presentations
10:30am - 11:00am ESTPipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation
Authors
Branden Butler
Sixing Yu
Arya Mazaheri
Ali Jannesari
Accelerators
Artificial Intelligence/Machine Learning
Distributed Computing
Heterogeneous Computing
Performance Optimization
11:00am - 11:30am ESTRecFlex: Enabling Feature Heterogeneity-Aware Optimization for Deep Recommendation Models with Flexible Schedules
Authors
Zaifeng Pan
Zhen Zheng
Feng Zhang
Bing Xie
Ruofan Wu
Shaden Smith
Chuanjie Liu
Olatunji Ruwase
Xiaoyong Du
Yufei Ding
Accelerators
Artificial Intelligence/Machine Learning
Distributed Computing
Heterogeneous Computing
Performance Optimization
11:30am - 12:00pm ESTParvaGPU: Efficient Spatial GPU Sharing for Large-Scale DNN Inference in Cloud Environments
Authors
Munkyu Lee
Sihoon Seong
Minki Kang
Jihyuk Lee
Gap-Joo Na
In-Geol Chun
Dimitrios Nikolopoulos
Cheol-Ho Hong
Accelerators
Artificial Intelligence/Machine Learning
Cloud Computing