Large language models (LLM) and the applications built around them have emerged as powerful tools for understanding and generating natural language. However, optimizing these models for maximum efficiency and performance remains a significant challenge.

This session introduces a solution: Optimize LLM workloads on target hardware using the Intel® Extension for Transformers* and Intel® Extension for PyTorch*.

The session also covers:

• An introduction to Intel Extension for Transformers and Intel Extension for PyTorch—two powerful libraries for enhancing AI workload performance on Intel platforms.
  
• Using API calls in the PyTorch extension to optimize LLM performance and memory use.
• Using the transformer extension's optimization features, such as model compression, neural speed, and neural chat, which is a framework to build customized chatbots.

Skill level: Novice
 

Choose from the following download options:

• Intel Extension for PyTorch from GitHub* or from the AI Tools selector
• Intel Extension for Transformers from GitHub
   

• Get Started with Intel Extension for PyTorch
• See All Code Samples