2 citations · 2 across the 5 of their papers we have counts for
5 papers
MACKO: Sparse Matrix-Vector Multiplication for Low Sparsity
Vladimír Macko, Vladimír Boža
Sparse Matrix-Vector Multiplication (SpMV) is a fundamental operation in the inference of sparse Large Language Models (LLMs). Because existing SpMV methods perform poorly under th…
Addition is almost all you need: Compressing large language models with double binary factorization
Vladimír Boža, Vladimír Macko
Binary quantization approaches, which replace weight matrices with binary matrices and substitute costly multiplications with cheaper additions, offer a computationally efficient a…
Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization
Vladimír Boža, Vladimír Macko
Neural networks are often challenging to work with due to their large size and complexity. To address this, various methods aim to reduce model size by sparsifying or decomposing w…
Fast and Effective Weight Update for Pruned Large Language Models
Vladimír Boža
Pruning large language models (LLMs) is a challenging task due to their enormous size. The primary difficulty is fine-tuning the model after pruning, which is needed to recover the…
Merging of neural networks
Martin Pašen, Vladimír Boža
We propose a simple scheme for merging two neural networks trained with different starting initialization into a single one with the same size as the original ones. We do this by c…