Saleh Ashkboos

Most-cited papers

GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
Elias Frantar, Saleh Ashkboos, T. Hoefler, Dan Alistarh
2022arXiv.org2,808 citations
Semantic Scholar
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
Saleh Ashkboos, Amirkeivan Mohtashami, Maximilian L. Croci, Bo Li +5 more
2024Neural Information Processing Systems778 citations
Semantic Scholar
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
Tim Dettmers, Ruslan Svirschevski, Vage Egiazarian, Denis Kuznedelev +5 more
2023International Conference on Learning Representations509 citations Open access
Semantic Scholar
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
Saleh Ashkboos, Maximilian L. Croci, Marcelo Gennari do Nascimento, T. Hoefler +1 more
2024International Conference on Learning Representations506 citations
Semantic Scholar
OPTQ: Accurate Quantization for Generative Pre-trained Transformers
Elias Frantar, Saleh Ashkboos, T. Hoefler, Dan Alistarh
2023International Conference on Learning Representations505 citations
Semantic Scholar
SparCML: High-Performance Sparse Communication for Machine Learning
Cédric Renggli, Saleh Ashkboos, Mehdi Aghagolzadeh, Dan Alistarh +1 more
2018International Conference for High Performance Computing, Networking, Storage and Analysis153 citations
Semantic Scholar
Flare: Flexible In-Network Allreduce
D. De Sensi, S. Di Girolamo, Saleh Ashkboos, Shi-Gang Li +1 more
2021International Conference for High Performance Computing, Networking, Storage and Analysis68 citations Open access
Semantic Scholar
QUIK: Towards End-to-end 4-Bit Inference on Generative Large Language Models
Saleh Ashkboos, Ilia Markov, Elias Frantar, Tingxuan Zhong +4 more
2023Conference on Empirical Methods in Natural Language Processing52 citations Open access
Semantic Scholar
Motif Prediction with Graph Neural Networks
Maciej Besta, Raphael Grob, Cesare Miglioli, Nico Bernold +7 more
2021Knowledge Discovery and Data Mining48 citations Open access
Semantic Scholar
Quartet: Native FP4 Training Can Be Optimal for Large Language Models
Roberto L. Castro, Andrei Panferov, Soroush Tabesh, Oliver Sieberling +4 more
2025Neural Information Processing Systems43 citations
Semantic Scholar
Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization
Vage Egiazarian, Roberto L. Castro, Denis Kuznedelev, Andrei Panferov +7 more
2025arXiv.org42 citations
Semantic Scholar
New Bounds For Distributed Mean Estimation and Variance Reduction
Peter Davies, Vijaykrishna Gurunanthan, Niusha Moshrefi, Saleh Ashkboos +1 more
2021International Conference on Learning Representations32 citations
Semantic Scholar
ENS-10: A Dataset For Post-Processing Ensemble Weather Forecast
Saleh Ashkboos, La-mei Huang, Nikoli Dryden, Tal Ben-Nun +4 more
2022Neural Information Processing Systems25 citations Open access
Semantic Scholar
HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs
Saleh Ashkboos, Mahdi Nikdan, Soroush Tabesh, Roberto L. Castro +2 more
2025Neural Information Processing Systems18 citations
Semantic Scholar
ProbGraph: High-Performance and High-Accuracy Graph Mining with Probabilistic Set Representations
Maciej Besta, Cesare Miglioli, P. S. Labini, Jakub Tětek +10 more
2022International Conference for High Performance Computing, Networking, Storage and Analysis14 citations Open access
Semantic Scholar
EfQAT: An Efficient Framework for Quantization-Aware Training
Saleh Ashkboos, Bram Verhoef, T. Hoefler, E. Eleftheriou +1 more
2024arXiv.org12 citations
Semantic Scholar
Distributed Variance Reduction with Optimal Communication
Peter Davies, Vijaykrishna Gurunathan, Niusha Moshrefi, Saleh Ashkboos +1 more
202011 citations
Semantic Scholar
STen: Productive and Efficient Sparsity in PyTorch
Andrei Ivanov, Nikoli Dryden, Tal Ben-Nun, Timo Schneider +2 more
2023ACM Transactions on Architecture and Code Optimization (TACO)7 citations Open access
Semantic Scholar
The spatial computer: A model for energy-efficient parallel computation
Lukas Gianinazzi, Tal Ben-Nun, Maciej Besta, Saleh Ashkboos +3 more
2022arXiv.org7 citations Open access
Semantic Scholar
Beyond Outliers: A Study of Optimizers Under Quantization
Georgios Vlassis, Saleh Ashkboos, Alexandra Volkova, T. Hoefler +1 more
2025arXiv.org6 citations
Semantic Scholar
Computational Bottlenecks of Training Small-scale Large Language Models
Saleh Ashkboos, Iman Mirzadeh, Keivan Alizadeh-Vahid, M. Sekhavat +3 more
2024ENLSP4 citations
Semantic Scholar
Distributed Mean Estimation with Optimal Error Bounds
Dan Alistarh, Saleh Ashkboos, Peter Davies
2020arXiv.org2 citations
Semantic Scholar
Degree-based Feature Is All You Need: Science4Cast Report
Milad Aghajohari, Mohammad Sadegh Akhondzadeh, Saleh Ashkboos, Kamran Chitsaz
20212021 IEEE International Conference on Big Data (Big Data)1 citations
Semantic Scholar
Energy-Optimal and Low-Depth Algorithmic Primitives for Spatial Dataflow Architectures
Lukas Gianinazzi, Tal Ben-Nun, Maciej Besta, Saleh Ashkboos +3 more
2025IEEE International Parallel and Distributed Processing Symposium0 citations
Semantic Scholar