Red Hat acquires tech to lower the cost of machine learning | Computer Weekly

"Their groundbreaking approach involved leveraging techniques like pruning and quantisation to optimise machine learning models, allowing ML models to run efficiently on readily available CPUs without sacrificing performance."

"These models are not only more efficient to train and deploy, but they also offer significant advantages in terms of customisation and adaptability."

"The acquisition is aimed at lowering the barrier to entry for organisations wanting to run ML workloads without relying on expensive GPU servers."

"Red Hat is pushing the idea of sparsification, which strategically removes unnecessary connections within a model, reducing size and computational requirements without sacrificing accuracy or performance."

Read at ComputerWeekly.com