LLM Efficient Inference in CPUs and Intel GPUs - Intel Neural Speed

Explore efficient inference techniques for Large Language Models (LLMs) on CPUs and Intel GPUs using Intel Neural Speed in this 30-minute video. Dive into the performance capabilities of Intel Extension for Transformers and gain practical insights through provided Jupyter notebooks. Learn how to optimize LLM inference for data science and machine learning applications, leveraging Intel's hardware-specific solutions. Access accompanying resources, including a Medium article and GitHub repositories, to deepen your understanding and implement the techniques discussed.