LLMOps: Intel OpenVino Toolkit Inference on CPU and GPU for Transformers

LLMOps: Intel OpenVino Toolkit Inference on CPU and GPU for Transformers

Learn how to leverage the Intel OpenVino toolkit for efficient inference of Transformer models on both CPU and GPU. This 28-minute video tutorial guides you through the process of installing the Intel OpenVino Runtime, converting a Transformer model, and performing inference on CPU and GPU. Gain practical insights into optimizing machine learning workflows for data science applications. Access the accompanying notebook on GitHub for hands-on experience with the demonstrated techniques.