Publications

Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation

Zhewei Yao, Xiaoxia Wu, Cheng Li, Stephen Youn, Yuxiong He

PDF Source Document

Deepspeed data efficiency: Improving deep learning model quality and training efficiency via efficient data sampling and routing

Conglong Li, Zhewei Yao, Xiaoxia Wu, Minjia Zhang, Connor Holmes, Cheng Li, Yuxiong He

PDF Source Document

A Comprehensive Study on Post-Training Quantization for Large Language Models

Zhewei Yao, Cheng Li, Xiaoxia Wu, Stephen Youn, Yuxiong He

Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases

Cheng Li, Xiaoxia Wu, Reza Yazdani Aminabadi, Zhewei Yao, Yuxiong He

DySR: Adaptive Super-Resolution via Algorithm and System Co-design

Syed Zawad, Cheng Li, Zhewei Yao, Elton Zheng, Yuxiong He, Feng Yan

PDF Source Document

Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformers

Zhewei Yao, Xiaoxia Wu, Conglong Li, Connor Holmes, Minjia Zhang, Cheng Li, Yuxiong He

PDF Project Source Document

Deepspeed inference: Enabling efficient inference of transformer models at unprecedented scale

Reza Yazdani Aminabadi, Samyam Rajbhandari, Minjia Zhang, Ammar Ahmad Awan, Cheng Li, Du Li, Elton Zheng, Jeff Rasley, Shaden Smith, Olatunji Ruwase, Yuxiong He

PDF Project Source Document

The Design and Implementation of a Scalable DL Benchmarking Platform (Best Paper Award)

Cheng Li, Abdul Dakkak, Jinjun Xiong, Wen-mei Hwu

PDF Code Project Slides

DLSpec: A Deep Learning Task Exchange Specification

Cheng Li, Abdul Dakkak, Jinjun Xiong, Wen-mei Hwu

PDF Project Slides Source Document

Benanza: Automatic μBenchmark Generation to Compute ''Lower-bound'' Latency and Inform Optimizations of Deep Learning Models on GPUs

Cheng Li, Abdul Dakkak, Jinjun Xiong, Wen-mei Hwu

PDF Project Slides Source Document

XSP: Across-Stack Profiling and Analysis of Machine Learning Models on GPUs (Best Paper Award)

Cheng Li, Abdul Dakkak, Jinjun Xiong, Wei Wei, Lingjie Xu, Wen-mei Hwu

PDF Project Slides Source Document

DLBricks: Composable Benchmark Generation to Reduce Deep Learning Benchmarking Effort on CPUs

Cheng Li, Abdul Dakkak, Jinjun Xiong, Wen-mei Hwu

PDF Project Slides

MLModelScope: Evaluate and Introspect Cognitive Pipelines

Cheng Li, Abdul Dakkak, Jinjun Xiong, Wen-mei Hwu

TrIMS: Transparent and Isolated Model Sharing for Low Latency Deep Learning Inference in Function as a Service Environments

Abdul Dakkak, Cheng Li, Simon Garcia de Gonzalo, Jinjun Xiong, Wen-mei Hwu

PDF Code Poster Slides

Accelerating Reduction and Scan Using Tensor Core Units

Abdul Dakkak, Cheng Li, Jinjun Xiong, Isaac Gelado, Wen-mei Hwu

PDF Code Project Slides

Evaluating Characteristics of CUDA Communication Primitives on High-Bandwidth Interconnects (Best Paper Award)

Carl Pearson, Abdul Dakkak, Sarah Hashash, Cheng Li, I-Hsin Chung, Jinjun Xiong, Wen-mei Hwu

PDF Code Project Slides

Accelerating Reduction Using Tensor Core Units

Abdul Dakkak, Cheng Li, Jinjun Xiong, Isaac Gelado, Wen-mei Hwu

PDF Code Project Slides

SCOPE: C3SR Systems Characterization and Benchmarking Framework

Carl Pearson, Abdul Dakkak, Cheng Li, Sarah Hashash, Jinjun Xiong, Wen-mei Hwu

PDF Code Project

Matrix Factorization on GPUs with Memory Optimization and Approximate Computing

Wei Tan, Shiyu Chang, Liana Fong, Cheng Li, Zijun Wang, LiangLiang Cao

RAI: A Scalable Project Submission System for Parallel Programming Courses

Abdul Dakkak, Carl Pearson, Cheng Li, Wen-mei Hwu

PDF Code Project

KLAP: Kernel launch aggregation and promotion for optimizing dynamic parallelism

Izzat El Hajj, Juan Gomez-Luna, Cheng Li, Li-Wen Chang, Dejan Milojicic, Wen-mei Hwu

PDF Code Project

DjiNN and Tonic: DNN as a Service and Its Implications for Future Warehouse Scale Computers

Johann Hauswald, Yiping Kang, Michael A. Laurenzano, Quan Chen, Cheng Li, Trevor Mudge, Ronald G. Dreslinski, Jason Mars, Lingjia Tang

Sirius: An Open End-to-End Voice and Vision Personal Assistant and Its Implications for Future Warehouse Scale Computers

Johann Hauswald, Michael A. Laurenzano, Yunqi Zhang, Cheng Li, Austin Rovinski, Arjun Khurana, Ronald G. Dreslinski, Trevor Mudge, Vinicius Petrucci1, Lingjia Tang, Jason Mars

Stochastic circuits for real-time image-processing applications

Armin Alaghi, Cheng Li, John P. Hayes