In collaboration with Microsoft and NVIDIA, we have built-in NVIDIA NIM microservices and NVIDIA AgentIQ toolkit into Azure AI Foundry—unlocking unprecedented effectivity, efficiency, and value optimization on your AI tasks.
I’m excited to share a serious leap ahead in how we develop and deploy AI. In collaboration with NVIDIA, we’ve built-in NVIDIA NIM microservices and NVIDIA AgentIQ toolkit into Azure AI Foundry—unlocking unprecedented effectivity, efficiency, and value optimization on your AI tasks.
A brand new period of AI effectivity
In at the moment’s fast-paced digital panorama, scaling AI functions calls for extra than simply innovation—it requires streamlined processes that ship speedy time-to-market with out compromising on efficiency. With enterprise AI tasks typically taking 9 to 12 months to maneuver from conception to manufacturing, each effectivity acquire counts. Our integration is designed to alter that by simplifying each step of the AI improvement lifecycle.
NVIDIA NIM on Azure AI Foundry
NVIDIA NIM™, a part of the NVIDIA AI Enterprise software program suite, is a set of easy-to-use microservices engineered for safe, dependable, and high-performance AI inferencing. Leveraging strong applied sciences corresponding to NVIDIA Triton Inference Server™, TensorRT™, TensorRT-LLM, and PyTorch, NIM microservices are constructed to scale seamlessly on managed Azure compute.
They present:
- Zero-configuration deployment: Get up and working rapidly with out-of-the-box optimization.
- Seamless Azure integration: Works effortlessly with Azure AI Agent Service and Semantic Kernel.
- Enterprise-grade reliability: Benefit from NVIDIA AI Enterprise assist for steady efficiency and safety.
- Scalable inference: Tap into Azure’s NVIDIA accelerated infrastructure for demanding workloads.
- Optimized workflows: Accelerate functions starting from massive language fashions to superior analytics.
Deploying these providers is straightforward. With only a few clicks—whether or not choosing fashions just like the Llama-3.3-70B-NIM or others from the mannequin catalog in Azure AI Foundry—you’ll be able to combine them immediately into your AI workflows and begin constructing generative AI functions that work flawlessly inside the Azure ecosystem.
Optimizing efficiency with NVIDIA AgentIQ
Once your NVIDIA NIM microservices are deployed, NVIDIA AgentIQ takes middle stage. This open-source toolkit is designed to seamlessly join, profile, and optimize groups of AI brokers, permits your techniques to run at peak efficiency. AgentIQ delivers:
- Profiling and optimization: Leverage real-time telemetry to fine-tune AI agent placement, lowering latency and compute overhead.
- Dynamic inference enhancements: Continuously acquire and analyze metadata—corresponding to predicted output tokens per name, estimated time to subsequent inference, and anticipated token lengths—to dynamically enhance agent efficiency.
- Integration with Semantic Kernel: Direct integration with Azure AI Foundry Agent Service additional empowers your brokers with enhanced semantic reasoning and activity execution capabilities.
This clever profiling not solely reduces compute prices but in addition boosts accuracy and responsiveness, so that each a part of your agentic AI workflow is optimized for fulfillment.
In addition, we’ll quickly be integrating the NVIDIA Llama Nemotron Reason open reasoning mannequin. NVIDIA Llama Nemotron Reason is a robust AI mannequin household designed for superior reasoning. According to NVIDIA, Nemotron excels at coding, advanced math, and scientific reasoning whereas understanding person intent and seamlessly calling instruments like search and translations to perform duties.
Real-world impression
Industry leaders are already witnessing the advantages of those improvements.
Drew McCombs, Vice President, Cloud and Analytics at Epic, famous:
The launch of NVIDIA NIM microservices in Azure AI Foundry presents a safe and environment friendly means for Epic to deploy open-source generative AI fashions that enhance affected person care, increase clinician and operational effectivity, and uncover new insights to drive medical innovation. In collaboration with UW Health and UC San Diego Health, we’re additionally researching strategies to guage scientific summaries with these superior fashions. Together, we’re utilizing the most recent AI know-how in ways in which actually enhance the lives of clinicians and sufferers.
Epic’s expertise underscores how our built-in answer can drive transformational change—not simply in healthcare however throughout each {industry} the place high-performance AI is a sport changer. As famous by Jon Sigler, EVP, Platform and AI at ServiceNow:
This mixture of ServiceNow’s AI platform with NVIDIA NIM and Microsoft Azure AI Foundry and Azure AI Agent Service helps us deliver to market industry-specific, out-of-the-box AI brokers, delivering full-stack agentic AI options to assist resolve issues sooner, ship nice buyer experiences, and speed up enhancements in organizations’ productiveness and effectivity.
Unlock AI-powered innovation
By combining the strong deployment capabilities of NVIDIA NIM with the dynamic optimization of NVIDIA AgentIQ, Azure AI Foundry gives a turnkey answer for constructing, deploying, and scaling enterprise-grade agentic functions. This integration can speed up AI deployments, improve agentic workflows, and scale back infrastructure prices—enabling you to concentrate on what actually issues: driving innovation.
Ready to speed up your AI journey?
Deploy NVIDIA NIM microservices and optimize your AI brokers with NVIDIA AgentIQ toolkit on Azure AI Foundry. Explore extra concerning the Azure AI Foundry mannequin catalog.
Let’s construct a wiser, sooner, and extra environment friendly future collectively.