Scalability RSS
Customize AI Models and Optimize for Real-Time Inference Serving at Scale with NVIDIA AI on Azure Machine Learning
Simplifying and accelerating AI model development workflows is hugely valuable, whether you have an army of data scientists or just a few developers. From adapting a model to fit your use-case to optimizing it for production deployment - it is a complex and iterative process. In this session, we'll show how easy it is to train and optimize an object detection model with NVIDIA TAO, a low-code AI toolkit, and deploy it for inference using the NVIDIA Triton Inference Server on Azure ML. AI captioning languages supported: Arabic, Bulgarian, Chinese Simplified, Czech, Danish, Dutch, English, Finnish, French, French Canadian, German, Greek,...
Tags
- All
- AGI
- AI
- AI Models
- Artificial Cognition
- Autism Spectrum
- Avatars
- Azure Open AI
- Bias Compensation
- cobots
- Cognition Enhancement
- Cognitive Bias
- DALL-E 2
- Deep Thought
- Digital Minds
- Ethical AI
- Finance
- Generative AI
- GPT-4
- GPT-5
- Ignite 2022
- Infrastructure
- John Koetsier
- Kosmos-1
- Microsoft Copilot
- Microsoft Power Virtual Agents
- Multimodal Large Language Model
- Real-Time Inferencing
- Sabine Hossenfelder
- Scalability
- Science
- Social Robots
- Storytelling