Bilge Acun

RESEARCH SCIENTIST | MENLO PARK, UNITED STATES

Bilge Acun is a Research Scientist at Facebook AI Research (FAIR). Her research interests include Systems for Machine Learning, Parallel and Distributed Computing, Energy Efficient Computing. She is working on making large-scale machine learning systems fast and efficient. Particularly, she works on two optimization areas to improve the system throughput and efficiency:System and hardware optimizations using accelerators i.e. GPUs / TPUs and

Algorithmic methods such as tensor compression.

Bilge received her Ph.D. degree in 2017 at the Department of Computer Science at Universtiy of Illinois at Urbana-Champaign. Her dissertation received the 2018 ACM SigHPC Dissertation Award Honorable Mention. Before joining Facebook, she worked at the IBM Thomas J. Watson Research Center as a Research Staff Member.

Bilge's Publications

June 14, 2024

NLP

SYSTEMS RESEARCH

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

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

June 14, 2024

June 07, 2024

CORE MACHINE LEARNING

SYSTEMS RESEARCH

Beyond Efficiency: Scaling AI Sustainably

Carole-Jean Wu, Bilge Acun, Ramya Raghavendra, Kim Hazelwood

June 07, 2024

June 03, 2024

SYSTEMS RESEARCH

CHAI: Clustered Head Attention for Efficient LLM Inference

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

June 03, 2024

July 12, 2022

Carbon Dependencies in Datacenter Design and Management

Bilge Acun, Aditya Sundarrajan, Benjamin Lee, Carole-Jean Wu, David Brooks, Fiodar Kazhamiaka, Kiwan Maeng, Manoj Chakkaravarthy

July 12, 2022