Zobrazeno 1 - 10
of 1 947
pro vyhledávání: '"A Acun"'
Autor:
Lee, Yejin, Sun, Anna, Hosmer, Basil, Acun, Bilge, Balioglu, Can, Wang, Changhan, Hernandez, Charles David, Puhrsch, Christian, Haziza, Daniel, Guessous, Driss, Massa, Francisco, Kahn, Jacob, Wan, Jeffrey, Reizenstein, Jeremy, Zhai, Jiaqi, Isaacson, Joe, Schlosser, Joel, Pino, Juan, Sadagopan, Kaushik Ram, Shamis, Leonid, Ma, Linjian, Hwang, Min-Jae, Chen, Mingda, Elhoushi, Mostafa, Rodriguez, Pedro, Pasunuru, Ram, Yih, Scott, Popuri, Sravya, Liu, Xing, Wu, Carole-Jean
Generative artificial intelligence (AI) technology is revolutionizing the computing industry. Not only its applications have broadened to various sectors but also poses new system design and optimization opportunities. The technology is capable of un
Externí odkaz:
http://arxiv.org/abs/2410.00215
Barroso's seminal contributions in energy-proportional warehouse-scale computing launched an era where modern datacenters have become more energy efficient and cost effective than ever before. At the same time, modern AI applications have driven ever
Externí odkaz:
http://arxiv.org/abs/2406.05303
A significant fraction (5-15%) of renewable energy generated goes into waste in the grids around the world today due to oversupply issues and transmission constraints. Being able to predict when and where renewable curtailment occurs would improve re
Externí odkaz:
http://arxiv.org/abs/2405.18526
Autor:
Golden, Alicia, Hsia, Samuel, Sun, Fei, Acun, Bilge, Hosmer, Basil, Lee, Yejin, DeVito, Zachary, Johnson, Jeff, Wei, Gu-Yeon, Brooks, David, Wu, Carole-Jean
Training large-scale machine learning models poses distinct system challenges, given both the size and complexity of today's workloads. Recently, many organizations training state-of-the-art Generative AI models have reported cases of instability dur
Externí odkaz:
http://arxiv.org/abs/2405.02803
Autor:
Elhoushi, Mostafa, Shrivastava, Akshat, Liskovich, Diana, Hosmer, Basil, Wasti, Bram, Lai, Liangzhen, Mahmoud, Anas, Acun, Bilge, Agarwal, Saurabh, Roman, Ahmed, Aly, Ahmed A, Chen, Beidi, Wu, Carole-Jean
We present LayerSkip, an end-to-end solution to speed-up inference of large language models (LLMs). First, during training we apply layer dropout, with low dropout rates for earlier layers and higher dropout rates for later layers, and an early exit
Externí odkaz:
http://arxiv.org/abs/2404.16710
Autor:
Agarwal, Saurabh, Acun, Bilge, Hosmer, Basil, Elhoushi, Mostafa, Lee, Yejin, Venkataraman, Shivaram, Papailiopoulos, Dimitris, Wu, Carole-Jean
Large Language Models (LLMs) with hundreds of billions of parameters have transformed the field of machine learning. However, serving these models at inference time is both compute and memory intensive, where a single request can require multiple GPU
Externí odkaz:
http://arxiv.org/abs/2403.08058
Recommendation algorithms have been pivotal in handling the overwhelming volume of online content. However, these algorithms seldom consider direct user input, resulting in superficial interaction between them. Efforts have been made to include the u
Externí odkaz:
http://arxiv.org/abs/2401.03605
Autor:
Golden, Alicia, Hsia, Samuel, Sun, Fei, Acun, Bilge, Hosmer, Basil, Lee, Yejin, DeVito, Zachary, Johnson, Jeff, Wei, Gu-Yeon, Brooks, David, Wu, Carole-Jean
As the development of large-scale Generative AI models evolve beyond text (1D) generation to include image (2D) and video (3D) generation, processing spatial and temporal information presents unique challenges to quality, performance, and efficiency.
Externí odkaz:
http://arxiv.org/abs/2312.14385
Autor:
Chen, Lingjiao, Acun, Bilge, Ardalani, Newsha, Sun, Yifan, Kang, Feiyang, Lyu, Hanrui, Kwon, Yongchan, Jia, Ruoxi, Wu, Carole-Jean, Zaharia, Matei, Zou, James
As Machine Learning (ML) systems continue to grow, the demand for relevant and comprehensive datasets becomes imperative. There is limited study on the challenges of data acquisition due to ad-hoc processes and lack of consistent methodologies. We fi
Externí odkaz:
http://arxiv.org/abs/2311.13712
Autor:
Xing, Jiali, Acun, Bilge, Sundarrajan, Aditya, Brooks, David, Chakkaravarthy, Manoj, Avila, Nikky, Wu, Carole-Jean, Lee, Benjamin C.
The increasing integration of renewable energy sources results in fluctuations in carbon intensity throughout the day. To mitigate their carbon footprint, datacenters can implement demand response (DR) by adjusting their load based on grid signals. H
Externí odkaz:
http://arxiv.org/abs/2311.08589