Deploy model to NVIDIA Triton Inference Server
|
NVIDIA Triton Inference Server is a multi-framework, open-source software that is optimized for inference. It supports popular machine learning frameworks like TensorFlow, Open Neural Network Exchange (ONNX) Runtime, PyTorch, NVIDIA TensorRT, and more. It can be used for your CPU or GPU workloads. In this module, you deploy your production model to NVIDIA Triton server to perform inference on a cloud-hosted virtual machine.
Create an NVIDIA GPU Accelerated Virtual Machine., Configure NVIDIA Triton Inference Server and related prerequisites., Execute an inference workload on NVIDIA Triton Inference Server.
Prerequisites
Azure Free Trial Account
User Reviews
Be the first to review “Deploy model to NVIDIA Triton Inference Server”
Related Products
Introducing Generative AI with AWS
Learn the fundamentals of generative AI and how to implement AWS services to create AI-driven applications.
Advanced Computer Vision and Deep Learning
Explore advanced topics in computer vision and deep learning techniques for complex image analysis tasks.
Introduction to Python for AI Programmers
Learn Python programming with a focus on applications in AI and machine learning development.
Ethical AI
Explore ethical considerations and frameworks for developing responsible AI systems that align with societal values.
Building a Reproducible Model Workflow
Explore best practices for creating reproducible workflows in machine learning model development.
Machine Learning Engineer with Microsoft Azure
Acquire the skills needed to build and deploy machine learning models using Microsoft Azure's tools and services.
There are no reviews yet.