Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Ashkboos, Saleh"'
Autor:
Ashkboos, Saleh, Mohtashami, Amirkeivan, Croci, Maximilian L., Li, Bo, Jaggi, Martin, Alistarh, Dan, Hoefler, Torsten, Hensman, James
We introduce QuaRot, a new Quantization scheme based on Rotations, which is able to quantize LLMs end-to-end, including all weights, activations, and KV cache in 4 bits. QuaRot rotates LLMs in a way that removes outliers from the hidden state without
Externí odkaz:
http://arxiv.org/abs/2404.00456
Autor:
Gianinazzi, Lukas, Ziogas, Alexandros Nikolaos, Huang, Langwen, Luczynski, Piotr, Ashkboos, Saleh, Scheidl, Florian, Carigiet, Armon, Ge, Chio, Abubaker, Nabil, Besta, Maciej, Ben-Nun, Tal, Hoefler, Torsten
Publikováno v:
PPoPP'24: Proceedings of the 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming (2024) 404-416
We propose a novel approach to iterated sparse matrix dense matrix multiplication, a fundamental computational kernel in scientific computing and graph neural network training. In cases where matrix sizes exceed the memory of a single compute node, d
Externí odkaz:
http://arxiv.org/abs/2402.19364
Autor:
Ashkboos, Saleh, Croci, Maximilian L., Nascimento, Marcelo Gennari do, Hoefler, Torsten, Hensman, James
Large language models have become the cornerstone of natural language processing, but their use comes with substantial costs in terms of compute and memory resources. Sparsification provides a solution to alleviate these resource constraints, and rec
Externí odkaz:
http://arxiv.org/abs/2401.15024
Autor:
Ashkboos, Saleh, Markov, Ilia, Frantar, Elias, Zhong, Tingxuan, Wang, Xincheng, Ren, Jie, Hoefler, Torsten, Alistarh, Dan
Large Language Models (LLMs) from the GPT family have become extremely popular, leading to a race towards reducing their inference costs to allow for efficient local computation. Yet, the vast majority of existing work focuses on weight-only quantiza
Externí odkaz:
http://arxiv.org/abs/2310.09259
Autor:
Dettmers, Tim, Svirschevski, Ruslan, Egiazarian, Vage, Kuznedelev, Denis, Frantar, Elias, Ashkboos, Saleh, Borzunov, Alexander, Hoefler, Torsten, Alistarh, Dan
Recent advances in large language model (LLM) pretraining have led to high-quality LLMs with impressive abilities. By compressing such LLMs via quantization to 3-4 bits per parameter, they can fit into memory-limited devices such as laptops and mobil
Externí odkaz:
http://arxiv.org/abs/2306.03078
As deep learning models grow, sparsity is becoming an increasingly critical component of deep neural networks, enabling improved performance and reduced storage. However, existing frameworks offer poor support for sparsity. Specialized sparsity engin
Externí odkaz:
http://arxiv.org/abs/2304.07613
Generative Pre-trained Transformer models, known as GPT or OPT, set themselves apart through breakthrough performance across complex language modelling tasks, but also by their extremely high computational and storage costs. Specifically, due to thei
Externí odkaz:
http://arxiv.org/abs/2210.17323
Autor:
Besta, Maciej, Miglioli, Cesare, Labini, Paolo Sylos, Tětek, Jakub, Iff, Patrick, Kanakagiri, Raghavendra, Ashkboos, Saleh, Janda, Kacper, Podstawski, Michal, Kwasniewski, Grzegorz, Gleinig, Niels, Vella, Flavio, Mutlu, Onur, Hoefler, Torsten
Publikováno v:
Proceedings of the ACM/IEEE International Conference on High Performance Computing, Networking, Storage and Analysis, November 2022
Important graph mining problems such as Clustering are computationally demanding. To significantly accelerate these problems, we propose ProbGraph: a graph representation that enables simple and fast approximate parallel graph mining with strong theo
Externí odkaz:
http://arxiv.org/abs/2208.11469
Autor:
Ashkboos, Saleh, Huang, Langwen, Dryden, Nikoli, Ben-Nun, Tal, Dueben, Peter, Gianinazzi, Lukas, Kummer, Luca, Hoefler, Torsten
Post-processing ensemble prediction systems can improve the reliability of weather forecasting, especially for extreme event prediction. In recent years, different machine learning models have been developed to improve the quality of weather post-pro
Externí odkaz:
http://arxiv.org/abs/2206.14786
Autor:
Gianinazzi, Lukas, Ben-Nun, Tal, Besta, Maciej, Ashkboos, Saleh, Baumann, Yves, Luczynski, Piotr, Hoefler, Torsten
We present a new parallel model of computation suitable for spatial architectures, for which the energy used for communication heavily depends on the distance of the communicating processors. In our model, processors have locations on a conceptual tw
Externí odkaz:
http://arxiv.org/abs/2205.04934