In cooperation with Microsoft and NVIDIA, we integrated NVIDIA Nim MicroServices and NVIDIA Agents Toolkit into Azure AI Foundry – Club unprecedented efficiency, performance and cost optimization for your AI projects.
I am excited to share a big jump forward in how we evolve and deploy AI. In cooperation with NVIDIA, we integrated NVIDIA Nim MicroServices and NVIDIA Agents – Toolkit Equipment into the Azure AI foundry – unprecedented blocking with efficiency, performance and optimization for your AI projects.
A new era of effectiveness AI
In today’s rapidly developing digital environment, AI applications require more than just an innovation-effective process that provides rapid time without endangering performance. Since corporate AI projects often last for 9 to 12 months before moving from design to production, each effective profit counts. Our integration is designed to change it by simplifying every step of the AI development cycle.
Nvidia nim on Azure Ai Foundry
Nvidia Nim ™, part of the NVIDIA AI Enterprise Software Set, monitors easy -to -use microservises for safe, reliable and high -performance AI infreenions. Using robust technologies such as NVIDIA TRITON INFERENCE SERVIS.
They provide:
- Deployment of zero configuration: Raise quickly and run out-of-the-box optimization.
- Easy Integration Azure: He works effortlessly with the Azure AI agent and the semantic core.
- LIVABILITY TO THE BUSINESS CLASS: Benefits of supporting NVIDIA AI Enterprise for continuous performance and security.
- Scalable Inference: Click the accelerated NVIDIA Azure infrastructure to enforce the workload.
- Optimized workflows: Accelerate applications from large language models to advanced analysis.

The deployment of these services is simple. With just a few clicks-and you already select models such as LLAMA-3.3-70B-NIM or other from the model catalog in Azure AI foundry-you can integrate them directly into your AI workflows and start creating generative AI applications that work flawlessly in Azure ecosystem.
Performance Optimization with NVIDIA Agentiq
Once your NVIDIA microservisses are deployed, NVIDIA AGENTIQ will take over a central internship. This open source tool set is designed to combine, profile and optimize AI agents, allows your systems to run at maximum power. AGRACTIVE DELIVERS:
- Profile and Optimization: Real time telemetry to gently tune the placement of AI AI, reduce latency and calculation of overhead costs.
- Dynamic Improvements of Inference: Constantly collect and analyze metadata – if the output tokens are predicted to the call, estimated time to the next conclusion and the expected length of the token – to dynamically improve the performance of the agent.
- Integration with semantic core: Direct integration with Azure AI Foundry Service also seizes your agents with increased semantic thinking and tasks.

This intelligent religion not only reduces computing costs, but also increases accuracy and sensitivity, so each part of your AI workflow is optimized for success.
In addition, we will soon integrate the model of open thinking NVIDIA LLAM NEOTRON. The reason for NVIDIA LLAM NEOTRON is a powerful AI model for advanced reasoning. According to Nvidia Nemotron, it excels in coding, complex mathematics and scientific reasoning and understanding the user’s intention and smoothly calling tools such as searching and translations to fulfill tasks.
Impact in the real world
The leaders in the field are already witnessed by the benefits of these innovations.
Drew McCombs, Vice President for Cloud and Analytics in Epic, awarded:
The launch of NVIDIA Nim MicroServices in Azure AI Foundry offers a safe and efficient way to deploy generative AI models with open source code that improve patient care, strengthen physicians and operational efficiency, and reveal new knowledge about medical innovation management. In cooperation with UW Health and UC San Diego Health, we are also exploring methods for evaluating clinical summary with these advanced models. Together we use the latest AI technology in a way that really improves the lives of clinics and patients.
EPIC’s experience underlines how our integrated solution can control transformation changes in healthcare, but in every industry where high-performance AI is a change in the game. As noted Sigl, EVP, Platform and AI in Servicenow:
This combination of AI Servicenow with Nvidia Nim and Microsoft Azure AI Foundry and Azure Ai Agent Service helps us bring us to market industries, AI agents, and supply full stack agents to help resolves faster, provide great centerSernes and Accelete Accelate and Accelerate and Accelate and Accelerate and Accelerate and Accelerate and Accelerate and improving the productivity and efficiency of organizations.
Unlock the innovation of driven A.
By combining the Robust NVIDIA deployment with the dynamic optimization of the NVIDIA Agentiq, Azure AI Foundry, it provides a turnkey solution for building, deployment and scaling of business agents. This integration can accelerate AI deployment, improve agent workflows and reduce the cost of infrastructure – allowing you to focus on what really matters: innovation management.
Are you ready to speed up your path AI?
Put on NVIDIA Nim MicroServices and optimize your AI agents using NVIDIA Agent Toolkit at Azure AA Foundry. Explore more about the Azure AI Foundry catalog.
Let’s build a smarter, faster and more efficient future together.