Deep Sparse

Sparsify Hugging Face BERT for Better CPU Performance & Smaller File Size

A Brief History of GPUs

Graphics processing units (GPUs) were popularized in the late 1990s and early 2000s by Nvidia and ATI (now a part of…

Welcome to Limitless AI

Throughout history, there have been two ways of solving problems: work within limits, or find ways to overcome them.

Pruning Hugging Face BERT: Using Compound Sparsification for Faster CPU Inference with Better Accuracy

Machine Learning Needs Academia and Industry to Survive: Neural Magic

Using CNNs for Inference — Neural Magic

Convolutional neural networks (CNNs) are a type of neural network most often used for…

The Challenges of EfficientNets And the Way Forward

Why Am I Using GPUs for Deep Learning Inference?

Or other domain-specific chipsets, for that matter?