Learn to accelerate and optimize AI/ML inference on LLMs using GPUs and batch processing, with potential vector database results. This talk covers production AI model powering.
Overview
Most production AI models using deep learning will be performing computational forward passes for inference. This demo will go into the steps you would take to accelerate and optimize inference on models like LLMs with the power of GPUs and batch processing. We may also be showing the results via a vector database.
