A low-code framework for developing cloud-native, real-time, and multimodal AI applications.
Microservices and Cloud-Native Applications
The Unified Compute Framework lets developers build and combine accelerated microservices across domains into real-time, multimodal AI applications. Every microservice has a bounded domain context (vision AI, conversational AI, data analytics, graphics rendering) and can be independently deployed, managed, and scaled within the application. The abstraction of each domain from the application reduces the need for low-level domain and platform knowledge.
UCF includes validated & deployment-ready microservices to accelerate application development. New and custom microservices can also be created using NVIDIA SDKs. In particular, in the context of XRECO, UCF will be used to generate pipelines with NERF calls. This system is being built in close collaboration with CERTH partner.
Low-Code Design Tools
UCF includes a set of low-code design tools to create, configure, and package applications for cloud deployment. Designs are visualized as a graph of data processing nodes. Using drag and drop operations, you can quickly create and combine these nodes to build powerful applications that incorporate different AI modalities, graphics, and other processing functions. Design rules and other validation checks built into the IDE ensure that UCF applications are correct-by-construction. This way, extended reality experts do not need to become experts in networking and workload deployments in cloud, but focus on their niche of expertise. Once complete, you can package UCF applications into containers and easily deploy them on the cloud or on-prem using Helm charts.
Cloud-Native AI Powered by UCF
UCF can be used beyond XRECO. Some examples of UCF include:
- NVIDIA Omniverse Avatar Cloud Engine (ACE) is a collection of cloud-based AI models and services to help developers easily build, customize, and deploy engaging and interactive avatars. The NVIDIA Tokkio intelligent AI-powered customer service agent and NVIDIA Maxine suite of GPU-accelerated AI SDKs and cloud-native microservices to enhance audio, video, and AR effects, use Omniverse ACE to help you build domain-specific avatar solutions.
- Clara Holoscan streamlines AI development and deployment for medical devices. Now, you can more easily build high-performance streaming AI applications for medical devices with the NVIDIA Clara Holoscan SDK. Access healthcare-specific acceleration libraries, pretrained AI models, and reference applications for ultrasound, endoscopy, surgical robots, and more.
- Metropolis Microservices is a suite of cloud-native microservices and reference applications for fast-tracking development and deployment of smart space solutions. It provides customizable cloud-native building blocks to build vision AI applications that unlock business insights for a wide range of spaces, ranging from roadways to airports to retail stores. Its reference applications can understand traffic flow, estimate building occupancy, create heatmaps, and more.
Follow XReco!