Join NVIDIA’s finance team for a thirty-minute session focused on how to optimize models for real-time inferencing. David Williams, an NVIDIA expert on model serving, will take a model from development into production and optimize it for low latency using NVIDIA® TensorRT™ 7.

• How to move models from development into inferencing mode using ONNX

• The adjustments you need to make to TensorRT for low-latency models

• How to serve and manage multiple low-latency models across multiple nodes and clusters

Content

content goes here