Picture for Guy Boudoukh

Guy Boudoukh

An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs

Add code
Jun 28, 2023
Viaarxiv icon

Fast DistilBERT on CPUs

Add code
Oct 27, 2022
Viaarxiv icon

Prune Once for All: Sparse Pre-Trained Language Models

Add code
Nov 10, 2021
Figure 1 for Prune Once for All: Sparse Pre-Trained Language Models
Figure 2 for Prune Once for All: Sparse Pre-Trained Language Models
Figure 3 for Prune Once for All: Sparse Pre-Trained Language Models
Figure 4 for Prune Once for All: Sparse Pre-Trained Language Models
Viaarxiv icon

Q8BERT: Quantized 8Bit BERT

Add code
Oct 17, 2019
Figure 1 for Q8BERT: Quantized 8Bit BERT
Figure 2 for Q8BERT: Quantized 8Bit BERT
Viaarxiv icon