Go to Tech Hub

Auto-scaling Hardware-agnostic ML Inference with NVIDIA Triton and Arm NN


SPEAKERS

Research Engineer
AI in Emerging Areas
Available from October 6

NVIDIA Triton Inference Server simplifies the deployment of AI models at scale in production. With the Arm NN backend, we can orchestrate multi-tenant ML model execution and enable optimized CPU/GPU configurations with Arm NN/TensorRT on embedded systems.

As Arm is scaling its computing power to the cloud, the solution will provide seamless AI inference workload distribution between edge and cloud.

In this session, we will introduce the solution architecture and its real-world applications.
SEE MORE

RELATED CONTENT


EVENT PARTNER SESSIONS

Keeping Up with the Times in Your Arm-based Application

Wei Xiao

AI in Emerging Areas / NVIDIA


The complexity of embedded applications has grown exponentially over the last decade. There are many reasons for this, but one of the biggest drivers is the relentless pursuit of greater functionality...

Go to Session

ON-DEMAND TECHNICAL SESSION

AI Accelerated User Experiences and Security with Windows on Snapdragon Compute Platforms

Wei Xiao

AI in Emerging Areas / NVIDIA


Available from October 6 The convergence of AI, 5G, and the cloud are creating incredible new use-cases and possibilities for the modern PC. The Snapdragon system-on-chip includes hardware engines, d...

Go to Session

WORKSHOPS

Get Started with Cloud-Native Automotive Software Development

Wei Xiao

AI in Emerging Areas / NVIDIA


This workshop, delivered by Arm and AWS, presents a guided tutorial for getting started with cloud-native technologies for development of software-defined vehicles. Leveraging architectural parity be...

Go to Session