GTC ON-DEMAND

 
SEARCH SESSIONS
SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC ON-DEMAND

Developer Tools
Presentation
Media
Maximizing Utilization for Data Center Inference with TensorRT Inference Server
Abstract:
As the use of AI has increased in applications, so has the need for production quality AI inference. The NVIDIA TensorRT Hyperscale Inference platform is designed precisely for this purpose, with a combination of hardware and software to meet the highest scalability and demand requirements. In this session, learn about the new TensorRT inference server, which maximizes utilization by allowing inference on multiple models on the same system, supports all popular AI frameworks, and integrates seamlessly into DevOps deployments using Docker, Kubernetes, and Kubeflow.
 
Topics:
Developer Tools
Type:
Talk
Event:
GTC Washington D.C.
Year:
2018
Session ID:
DC8227
Streaming:
Share: