Sayeh Sharify

According to our database, Sayeh Sharify authored at least 25 papers between 2017 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals.

Utkarsh Saxena, Sayeh Sharify, Kaushik Roy, Xin Wang

CoRR, 2024

Understanding the difficulty of low-precision post-training quantization of large language models.

Zifei Xu, Sayeh Sharify, Wanzin Yazar, Tristan Webb, Xin Wang

CoRR, 2024

Scaling laws for post-training quantized large language models.

Zifei Xu, Alexander Lan, Wanzin Yazar, Tristan Webb, Sayeh Sharify, Xin Wang

CoRR, 2024

Combining multiple post-training techniques to achieve most efficient quantized LLMs.

Sayeh Sharify, Zifei Xu, Wanzin Yazar, Xin Wang

CoRR, 2024

Self-Selected Attention Span for Accelerating Large Language Model Inference.

Tian Jin, Wanzin Yazar, Zifei Xu, Sayeh Sharify, Xin Wang

CoRR, 2024

2023

Mixed-Precision Quantization with Cross-Layer Dependencies.

Zihao Deng, Xin Wang, Sayeh Sharify, Michael Orshansky

CoRR, 2023

2021

Boveda: Building an On-Chip Deep Learning Memory Hierarchy Brick by Brick.

Isak Edo Vivancos, Sayeh Sharify, Daniel Ly-Ma, Ameer Abdelhadi, Ciaran Bannon, Milos Nikolic, Mostafa Mahmoud, Alberto Delmas Lascorz, Gennady Pekhimenko, Andreas Moshovos

Proceedings of the Fourth Conference on Machine Learning and Systems, 2021

2020

Late Breaking Results: Building an On-Chip Deep Learning Memory Hierarchy Brick by Brick.

Isak Edo Vivancos, Sayeh Sharify, Milos Nikolic, Ciaran Bannon, Mostafa Mahmoud, Alberto Delmas Lascorz, Andreas Moshovos

Proceedings of the 57th ACM/IEEE Design Automation Conference, 2020

2019

Accelerating Image-Sensor-Based Deep Learning Applications.

Mostafa Mahmoud, Dylan Malone Stuart, Zissis Poulos, Alberto Delmas Lascorz, Patrick Judd, Sayeh Sharify, Milos Nikolic, Kevin Siu, Isak Edo Vivancos, Jorge Albericio, Andreas Moshovos

IEEE Micro, 2019

ShapeShifter: Enabling Fine-Grain Data Width Adaptation in Deep Learning.

Alberto Delmas Lascorz, Sayeh Sharify, Isak Edo Vivancos, Dylan Malone Stuart, Omar Mohamed Awad, Patrick Judd, Mostafa Mahmoud, Milos Nikolic, Kevin Siu, Zissis Poulos, Andreas Moshovos

Proceedings of the 52nd Annual IEEE/ACM International Symposium on Microarchitecture, 2019

Laconic deep learning inference acceleration.

Sayeh Sharify, Alberto Delmas Lascorz, Mostafa Mahmoud, Milos Nikolic, Kevin Siu, Dylan Malone Stuart, Zissis Poulos, Andreas Moshovos

Proceedings of the 46th International Symposium on Computer Architecture, 2019

Bit-Tactical: A Software/Hardware Approach to Exploiting Value and Bit Sparsity in Neural Networks.

Alberto Delmas Lascorz, Patrick Judd, Dylan Malone Stuart, Zissis Poulos, Mostafa Mahmoud, Sayeh Sharify, Milos Nikolic, Kevin Siu, Andreas Moshovos

Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems, 2019

2018

Value-Based Deep-Learning Acceleration.

Andreas Moshovos, Jorge Albericio, Patrick Judd, Alberto Delmas Lascorz, Sayeh Sharify, Tayler H. Hetherington, Tor M. Aamodt, Natalie D. Enright Jerger

IEEE Micro, 2018

Laconic Deep Learning Computing.

Sayeh Sharify, Mostafa Mahmoud, Alberto Delmas Lascorz, Milos Nikolic, Andreas Moshovos

CoRR, 2018

DPRed: Making Typical Activation Values Matter In Deep Learning Computing.

Alberto Delmas, Sayeh Sharify, Patrick Judd, Milos Nikolic, Andreas Moshovos

CoRR, 2018

Bit-Tactical: Exploiting Ineffectual Computations in Convolutional Neural Networks: Which, Why, and How.

Alberto Delmas, Patrick Judd, Dylan Malone Stuart, Zissis Poulos, Mostafa Mahmoud, Sayeh Sharify, Milos Nikolic, Andreas Moshovos

CoRR, 2018

Exploiting Typical Values to Accelerate Deep Learning.

Andreas Moshovos, Jorge Albericio, Patrick Judd, Alberto Delmas Lascorz, Sayeh Sharify, Zissis Poulos, Tayler H. Hetherington, Tor M. Aamodt, Natalie D. Enright Jerger

Computer, 2018

Identifying and Exploiting Ineffectual Computations to Enable Hardware Acceleration of Deep Learning.

Andreas Moshovos, Jorge Albericio, Patrick Judd, Alberto Delmas, Sayeh Sharify, Mostafa Mahmoud, Tayler H. Hetherington, Milos Nikolic, Dylan Malone Stuart, Kevin Siu, Zissis Poulos, Tor M. Aamodt, Natalie D. Enright Jerger

Proceedings of the 16th IEEE International New Circuits and Systems Conference, 2018

Loom: exploiting weight and activation precisions to accelerate convolutional neural networks.

Sayeh Sharify, Alberto Delmas Lascorz, Kevin Siu, Patrick Judd, Andreas Moshovos

Proceedings of the 55th Annual Design Automation Conference, 2018

2017

Loom: Exploiting Weight and Activation Precisions to Accelerate Convolutional Neural Networks.

Sayeh Sharify, Alberto Delmas Lascorz, Patrick Judd, Andreas Moshovos

CoRR, 2017

Cnvlutin2: Ineffectual-Activation-and-Weight-Free Deep Neural Network Computing.

Patrick Judd, Alberto Delmas Lascorz, Sayeh Sharify, Andreas Moshovos

CoRR, 2017

Tartan: Accelerating Fully-Connected and Convolutional Layers in Deep Learning Networks by Exploiting Numerical Precision Variability.

Alberto Delmas, Sayeh Sharify, Patrick Judd, Andreas Moshovos

CoRR, 2017

Dynamic Stripes: Exploiting the Dynamic Precision Requirements of Activation Values in Neural Networks.

Alberto Delmas, Patrick Judd, Sayeh Sharify, Andreas Moshovos

CoRR, 2017

Bit-pragmatic deep neural network computing.

Jorge Albericio, Alberto Delmas, Patrick Judd, Sayeh Sharify, Gerard O'Leary, Roman Genov, Andreas Moshovos

Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchitecture, 2017

Bit-Pragmatic Deep Neural Network Computing.

Jorge Albericio, Patrick Judd, Alberto Delmas, Sayeh Sharify, Andreas Moshovos

Proceedings of the 5th International Conference on Learning Representations, 2017