Deep Learning with Yacine on MSNOpinion

Reduced Row Echelon Form (RREF) in Python – Algorithm from Scratch

Learn how to implement the Reduced Row Echelon Form (RREF) algorithm from scratch in Python! Step-by-step, we’ll cover the ...
IEEE

Accelerating Sparse Matrix-Matrix Multiplication by Adaptive Batching Strategy on MGPUSim

Abstract: Sparse Matrix-Matrix Multiplication (SpMM) is a widely used algorithm in Machine Learning, particularly in the increasingly popular Graph Neural Networks (GNNs). SpMM is an essential ...
GitHub

at::Tensor::to_sparse_csr() does not produce correct result in Debug configuration when tensor is big sparse CSC on CUDA device in LibTorch 2.8.0

The issue is not present in standard pre-built LibTorch package. We had to compile Libtorch 2.8.0 from source, since CUDA support for sparse CSR tensor is in beta and not part of official distribution ...
IEEE

HyMM: A Hybrid Sparse-Dense Matrix Multiplication Accelerator for GCNs

Abstract: Graph convolutional networks (GCNs) are emerging neural network models designed to process graph-structured data. Due to massively parallel computations using irregular data structures by ...