关注
Reza Yazdani Aminabadi
Reza Yazdani Aminabadi
Microsoft Research
在 microsoft.com 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
Using deepspeed and megatron to train megatron-turing nlg 530b, a large-scale generative language model
S Smith, M Patwary, B Norick, P LeGresley, S Rajbhandari, J Casper, ...
arXiv preprint arXiv:2201.11990, 2022
5282022
{Zero-offload}: Democratizing {billion-scale} model training
J Ren, S Rajbhandari, RY Aminabadi, O Ruwase, S Yang, M Zhang, D Li, ...
2021 USENIX Annual Technical Conference (USENIX ATC 21), 551-564, 2021
2692021
Zeroquant: Efficient and affordable post-training quantization for large-scale transformers
Z Yao, R Yazdani Aminabadi, M Zhang, X Wu, C Li, Y He
Advances in Neural Information Processing Systems 35, 27168-27183, 2022
2302022
Deepspeed-inference: enabling efficient inference of transformer models at unprecedented scale
RY Aminabadi, S Rajbhandari, AA Awan, C Li, D Li, E Zheng, O Ruwase, ...
SC22: International Conference for High Performance Computing, Networking …, 2022
1652022
Deepspeed-moe: Advancing mixture-of-experts inference and training to power next-generation ai scale
S Rajbhandari, C Li, Z Yao, M Zhang, RY Aminabadi, AA Awan, J Rasley, ...
International conference on machine learning, 18332-18346, 2022
1592022
An ultra low-power hardware accelerator for automatic speech recognition
R Yazdani, A Segura, JM Arnau, A Gonzalez
Microarchitecture (MICRO), 2016 49th Annual IEEE/ACM International Symposium on, 2016
532016
The Dark Side of DNN Pruning
R Yazdani, M Riera, JM Arnau, A Gonzalez
The 45th International Symposium on Computer Architecture - ISCA 2018 1 (1), 2018
342018
Deepspeed-chat: Easy, fast and affordable rlhf training of chatgpt-like models at all scales
Z Yao, RY Aminabadi, O Ruwase, S Rajbhandari, X Wu, AA Awan, ...
arXiv preprint arXiv:2308.01320, 2023
332023
Multi-objective interior design optimization method based on sustainability concepts for post-disaster temporary housing units
SMA Hosseini, R Yazdani, A de la Fuente
Building and environment 173, 106742, 2020
312020
Low-Power Automatic Speech Recognition Through a Mobile GPU and a Viterbi Accelerator
R Yazdani, A Segura, JM Arnau, A Gonzalez
IEEE Micro 37 (01), 22-29, 2017
192017
Understanding int4 quantization for transformer models: Latency speedup, composability, and failure cases
X Wu, C Li, RY Aminabadi, Z Yao, Y He
arXiv preprint arXiv:2301.12017, 2023
182023
LSTM-sharp: An adaptable, energy-efficient hardware accelerator for long short-term memory
R Yazdani, O Ruwase, M Zhang, Y He, JM Arnau, A González
arXiv preprint arXiv:1911.01258, 2019
172019
UNFOLD: A Memory-Efficient Speech Recognizer Using On-The-Fly WFST Composition
R Yazdani, JM Arnau, A Gonzalez
IEEE/ACM International Symposium on Microarchitecture (MICRO'50), 2017
152017
Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B
S Smith, M Patwary, B Norick, P LeGresley, S Rajbhandari, J Casper, ...
A large-scale generative language model, 2022
122022
Using deepspeed and megatron to train megatron-turing nlg 530b, a large-scale generative language model. arXiv
S Smith, M Patwary, B Norick, P LeGresley, S Rajbhandari, J Casper, ...
Preprint published online January 28, 2022
122022
A low-power, high-performance speech recognition accelerator
R Yazdani, JM Arnau, A González
IEEE Transactions on Computers 68 (12), 1817-1831, 2019
122019
Understanding int4 quantization for language models: latency speedup, composability, and failure cases
X Wu, C Li, RY Aminabadi, Z Yao, Y He
International Conference on Machine Learning, 37524-37539, 2023
102023
Fault-Tolerant 3-D Network-on-Chip Design using Dynamic Link Sharing
SHS Rezaei, M Modarressi, R Yazdani, M Daneshtalab
Design, Automation & Test in Europe Conference & Exhibition (DATE) 1, 1195-1200, 2016
102016
Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A large-scale generative language model (arXiv: 2201.11990). arXiv
S Smith, M Patwary, B Norick, P LeGresley, S Rajbhandari, J Casper, ...
62022
LAWS: Locality-AWare Scheme for Automatic Speech Recognition
R Yazdani, JM Arnau, A Gonzalez
IEEE Transactions on Computers, 2020
62020
系统目前无法执行此操作,请稍后再试。
文章 1–20