Mostafa Elhoushi

RESEARCH ENGINEER | TORONTO, CANADA

I am a research engineer in FAIR Systems and Machine Learning (SysML) group. I focus on reserach that makes deep learning inference or training faster. Prior to joining FAIR, I was in the compilers team of Meta's Training and Inference Accelerator (MTIA) chip. I graduated from Ain Shams University, Egypt with my Bachelors and Masters, and obtained my PhD from Queen's University, Canada.

Mostafa's Work

Mostafa's Publications

June 14, 2024

NLP

SYSTEMS RESEARCH

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

Mostafa Elhoushi, Ahmed Aly, Akshat Shrivastava, Basil Hosmer, Beidi Chen, Bilge Acun, Bram Wasti, Carole-Jean Wu, Diana Liskovich, Liangzhen Lai, Ahmed Roman, Nas Mahmoud, Saurabh Agarwal

June 14, 2024

June 03, 2024

SYSTEMS RESEARCH

CHAI: Clustered Head Attention for Efficient LLM Inference

Saurabh Agarwal, Bilge Acun, Basil Hosmer, Carole-Jean Wu, Mostafa Elhoushi, Yejin Lee

June 03, 2024

April 03, 2024

COMPUTER VISION

Sieve: Multimodal Dataset Pruning Using Image Captioning Models

Anas Mahmoud, Amro Abbas, Yu Yang, Ari Morcos, Mostafa Elhoushi, Hugh Leather, Newsha Ardalani

April 03, 2024

July 26, 2023

SYSTEMS RESEARCH

Learning Compiler Pass Orders using Coreset and Normalized Value Prediction

Pengtao Xie, Kevin Stone, Chris Cummins, Hugh Leather, Jiadong Guo, Mostafa Elhoushi, Youwei Liang, Yuandong Tian

July 26, 2023

June 19, 2023

SYSTEMS RESEARCH

MODeL: Memory Optimizations for Deep Learning

Benoit Steiner, Jacob Kahn, James Hegarty, Mostafa Elhoushi

June 19, 2023