Saleh Ashkboos
Citata da
Citata da
OPTQ: Accurate quantization for generative pre-trained transformers
E Frantar, S Ashkboos, T Hoefler, D Alistarh
The Eleventh International Conference on Learning Representations, 2022
SparCML: High-performance sparse communication for machine learning
C Renggli, S Ashkboos, M Aghagolzadeh, D Alistarh, T Hoefler
Proceedings of the International Conference for High Performance Computing …, 2019
Spqr: A sparse-quantized representation for near-lossless llm weight compression
T Dettmers, R Svirschevski, V Egiazarian, D Kuznedelev, E Frantar, ...
arXiv preprint arXiv:2306.03078, 2023
Flare: Flexible in-network allreduce
D De Sensi, S Di Girolamo, S Ashkboos, S Li, T Hoefler
Proceedings of the International Conference for High Performance Computing …, 2021
New bounds for distributed mean estimation and variance reduction
P Davies, V Gurunathan, N Moshrefi, S Ashkboos, D Alistarh
arXiv preprint arXiv:2002.09268, 2020
Motif prediction with graph neural networks
M Besta, R Grob, C Miglioli, N Bernold, G Kwasniewski, G Gjini, ...
Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and …, 2022
Ens-10: A dataset for post-processing ensemble weather forecasts
S Ashkboos, L Huang, N Dryden, T Ben-Nun, P Dueben, L Gianinazzi, ...
Advances in Neural Information Processing Systems 35, 21974-21987, 2022
Slicegpt: Compress large language models by deleting rows and columns
S Ashkboos, ML Croci, MG Nascimento, T Hoefler, J Hensman
arXiv preprint arXiv:2401.15024, 2024
Probgraph: High-performance and high-accuracy graph mining with probabilistic set representations
M Besta, C Miglioli, PS Labini, J Tětek, P Iff, R Kanakagiri, S Ashkboos, ...
SC22: International Conference for High Performance Computing, Networking …, 2022
Towards end-to-end 4-bit inference on generative large language models
S Ashkboos, I Markov, E Frantar, T Zhong, X Wang, J Ren, T Hoefler, ...
arXiv preprint arXiv:2310.09259, 2023
The spatial computer: A model for energy-efficient parallel computation
L Gianinazzi, T Ben-Nun, M Besta, S Ashkboos, Y Baumann, P Luczynski, ...
arXiv preprint arXiv:2205.04934, 2022
Multi-way sparsest cut problem on trees with a control on the number of parts and outliers
R Javadi, S Ashkboos
Discrete Applied Mathematics 289, 281-291, 2021
Minimum cuts of distance-regular digraphs
S Ashkboos, G Omidi, F Shafiei, K Tajbakhsh
the electronic journal of combinatorics, P4. 2-P4. 2, 2017
An Efficient Parallel Data Clustering Algorithm Using Isoperimetric Number of Trees
R Javadi, S Ashkboos
arXiv preprint arXiv:1702.04739, 2017
STen: Productive and Efficient Sparsity in PyTorch
A Ivanov, N Dryden, T Ben-Nun, S Ashkboos, T Hoefler
arXiv preprint arXiv:2304.07613, 2023
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
S Ashkboos, A Mohtashami, ML Croci, B Li, M Jaggi, D Alistarh, T Hoefler, ...
arXiv preprint arXiv:2404.00456, 2024
Arrow Matrix Decomposition: A Novel Approach for Communication-Efficient Sparse Matrix Multiplication
L Gianinazzi, AN Ziogas, L Huang, P Luczynski, S Ashkboosh, F Scheidl, ...
Proceedings of the 29th ACM SIGPLAN Annual Symposium on Principles and …, 2024
Report on software performance benchmarking for ML solutions from deliverable D1. 3
N Dryden, T Ben-Nun, S Ashkboos, F Emmerich, J Jauch
First version of workflow tools published that allows to perform quarterly benchmarks of ML solutions
M Abel, S Ashkboos, T Ben-Nun, M Chantry, G Denisenko, F Emmerich
Il sistema al momento non può eseguire l'operazione. Riprova più tardi.
Articoli 1–19