Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Liu Ke

Liu Ke
Alert button

Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference


Mar 10, 2023
Haiyang Huang, Newsha Ardalani, Anna Sun, Liu Ke, Hsien-Hsin S. Lee, Anjali Sridhar, Shruti Bhosale, Carole-Jean Wu, Benjamin Lee

Add code
Alert button

Figure 1 for Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference
Figure 2 for Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference
Figure 3 for Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference
Figure 4 for Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Data Leakage via Access Patterns of Sparse Features in Deep Learning-based Recommendation Systems


Dec 12, 2022
Hanieh Hashemi, Wenjie Xiong, Liu Ke, Kiwan Maeng, Murali Annavaram, G. Edward Suh, Hsien-Hsin S. Lee

Add code
Alert button

Figure 1 for Data Leakage via Access Patterns of Sparse Features in Deep Learning-based Recommendation Systems
Figure 2 for Data Leakage via Access Patterns of Sparse Features in Deep Learning-based Recommendation Systems
Figure 3 for Data Leakage via Access Patterns of Sparse Features in Deep Learning-based Recommendation Systems
Figure 4 for Data Leakage via Access Patterns of Sparse Features in Deep Learning-based Recommendation Systems

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Neural Network-Inspired Analog-to-Digital Conversion to Achieve Super-Resolution with Low-Precision RRAM Devices


Nov 28, 2019
Weidong Cao, Liu Ke, Ayan Chakrabarti, Xuan Zhang

Add code
Alert button

Figure 1 for Neural Network-Inspired Analog-to-Digital Conversion to Achieve Super-Resolution with Low-Precision RRAM Devices
Figure 2 for Neural Network-Inspired Analog-to-Digital Conversion to Achieve Super-Resolution with Low-Precision RRAM Devices
Figure 3 for Neural Network-Inspired Analog-to-Digital Conversion to Achieve Super-Resolution with Low-Precision RRAM Devices
Figure 4 for Neural Network-Inspired Analog-to-Digital Conversion to Achieve Super-Resolution with Low-Precision RRAM Devices
* 7 pages, ICCAD 2019 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

AxTrain: Hardware-Oriented Neural Network Training for Approximate Inference


May 21, 2018
Xin He, Liu Ke, Wenyan Lu, Guihai Yan, Xuan Zhang

Add code
Alert button

Figure 1 for AxTrain: Hardware-Oriented Neural Network Training for Approximate Inference
Figure 2 for AxTrain: Hardware-Oriented Neural Network Training for Approximate Inference
Figure 3 for AxTrain: Hardware-Oriented Neural Network Training for Approximate Inference
Figure 4 for AxTrain: Hardware-Oriented Neural Network Training for Approximate Inference
* In International Symposium on Low Power Electronics and Design (ISLPED) 2018 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email