Zobrazeno 1 - 10
of 96
pro vyhledávání: '"Yazdanbakhsh, Amir"'
Autor:
TehraniJamsaz, Ali, Bhattacharjee, Arijit, Chen, Le, Ahmed, Nesreen K., Yazdanbakhsh, Amir, Jannesari, Ali
Recent advancements in Large Language Models (LLMs) have renewed interest in automatic programming language translation. Encoder-decoder transformer models, in particular, have shown promise in translating between different programming languages. How
Externí odkaz:
http://arxiv.org/abs/2410.20527
Autoregressive Large Language Models (LLMs) have achieved impressive performance in language tasks but face two significant bottlenecks: (1) quadratic complexity in the attention module as the number of tokens increases, and (2) limited efficiency du
Externí odkaz:
http://arxiv.org/abs/2406.07368
Autor:
You, Haoran, Guo, Yipin, Fu, Yichao, Zhou, Wei, Shi, Huihong, Zhang, Xiaofan, Kundu, Souvik, Yazdanbakhsh, Amir, Lin, Yingyan Celine
Large language models (LLMs) have shown impressive performance on language tasks but face challenges when deployed on resource-constrained devices due to their extensive parameters and reliance on dense multiplications, resulting in high memory deman
Externí odkaz:
http://arxiv.org/abs/2406.05981
Autor:
Harma, Simla Burcu, Chakraborty, Ayan, Kostenok, Elizaveta, Mishin, Danila, Ha, Dongho, Falsafi, Babak, Jaggi, Martin, Liu, Ming, Oh, Yunho, Subramanian, Suvinay, Yazdanbakhsh, Amir
The increasing size of deep neural networks necessitates effective model compression to improve computational efficiency and reduce their memory footprint. Sparsity and quantization are two prominent compression methods that have individually demonst
Externí odkaz:
http://arxiv.org/abs/2405.20935
We propose SLoPe, a Double-Pruned Sparse Plus Lazy Low-rank Adapter Pretraining method for LLMs that improves the accuracy of sparse LLMs while accelerating their pretraining and inference and reducing their memory footprint. Sparse pretraining of LL
Externí odkaz:
http://arxiv.org/abs/2405.16325
Microarchitecture simulators are indispensable tools for microarchitecture designers to validate, estimate, and optimize new hardware that meets specific design requirements. While the quest for a fast, accurate and detailed microarchitecture simulat
Externí odkaz:
http://arxiv.org/abs/2404.10921
Autor:
Kim, Yoonsung, Oh, Changhun, Hwang, Jinwoo, Kim, Wonung, Oh, Seongryong, Lee, Yubin, Sharma, Hardik, Yazdanbakhsh, Amir, Park, Jongse
Publikováno v:
ISCA 2024
Deep neural network (DNN) video analytics is crucial for autonomous systems such as self-driving vehicles, unmanned aerial vehicles (UAVs), and security robots. However, real-world deployment faces challenges due to their limited computational resour
Externí odkaz:
http://arxiv.org/abs/2403.14353
Autor:
Bambhaniya, Abhimanyu Rajeshkumar, Yazdanbakhsh, Amir, Subramanian, Suvinay, Kao, Sheng-Chun, Agrawal, Shivani, Evci, Utku, Krishna, Tushar
N:M Structured sparsity has garnered significant interest as a result of relatively modest overhead and improved efficiency. Additionally, this form of sparsity holds considerable appeal for reducing the memory footprint owing to their modest represe
Externí odkaz:
http://arxiv.org/abs/2402.04744
Autor:
Ding, Shaojin, Qiu, David, Rim, David, He, Yanzhang, Rybakov, Oleg, Li, Bo, Prabhavalkar, Rohit, Wang, Weiran, Sainath, Tara N., Han, Zhonglin, Li, Jian, Yazdanbakhsh, Amir, Agrawal, Shivani
End-to-end automatic speech recognition (ASR) models have seen revolutionary quality gains with the recent development of large-scale universal speech models (USM). However, deploying these massive USMs is extremely expensive due to the enormous memo
Externí odkaz:
http://arxiv.org/abs/2312.08553
Autor:
Lee, Joo Hyung, Park, Wonpyo, Mitchell, Nicole, Pilault, Jonathan, Obando-Ceron, Johan, Kim, Han-Byul, Lee, Namhoon, Frantar, Elias, Long, Yun, Yazdanbakhsh, Amir, Agrawal, Shivani, Subramanian, Suvinay, Wang, Xin, Kao, Sheng-Chun, Zhang, Xingyao, Gale, Trevor, Bik, Aart, Han, Woohyun, Ferev, Milen, Han, Zhonglin, Kim, Hong-Seok, Dauphin, Yann, Dziugaite, Gintare Karolina, Castro, Pablo Samuel, Evci, Utku
This paper introduces JaxPruner, an open-source JAX-based pruning and sparse training library for machine learning research. JaxPruner aims to accelerate research on sparse neural networks by providing concise implementations of popular pruning and s
Externí odkaz:
http://arxiv.org/abs/2304.14082