Computer Vision Meetup: Accelerating Multimodal RAG Pipelines with NVIDIA and OSS Integrations

Learn how to supercharge your multimodal Retrieval-Augmented Generation (RAG) pipelines by combining NVIDIA’s GPU-accelerated tools with powerful open-source technologies. This talk will demonstrate the seamless integration of NVIDIA’s optimized inference tools like TensorRT-LLM with popular community tools to create high-performance applications. We’ll explore how this synergy dramatically enhances processing speed and accuracy across text, image, and other modalities. Join us to learn how you can leverage this integrated approach to build scalable, efficient, and state-of-the-art multimodal AI applications.
About the Speaker
Jay Rodge is a developer advocate for large language models (LLMs), where he demonstrates how developers can leverage GPU acceleration in their LLM workflows, using widely used tools and frameworks.