Deploying Deep Learning Models for Inference at Production Scale

Explore a comprehensive session from NVIDIA Discovery Bengaluru focused on deploying AI models at production scale. Learn about two key NVIDIA resources: TensorRT, a deep learning platform optimizing neural network models and accelerating inference across GPU platforms, and Triton Inference Server, an open-source software providing a standardized inference platform for various infrastructures. Access the accompanying PowerPoint presentation for detailed insights. Gain valuable knowledge on the latest advancements in AI, machine learning, deep learning, and generative AI by joining the Applied Singularity Meetup group and downloading their free mobile app available on iOS and Android.

Deploying Deep Learning Models for Inference at Production Scale - at NVIDIA