NVIDIA Offers Free AI Model Endpoints to Developer Program Members

NVIDIA has announced that its NVIDIA NIM ( Neural Infrastructure for Mothership) is now free to over 5 million members of its Developer Program. This move aims to provide developers and engineering teams with easier access to rapidly deploy their AI model endpoints for accelerated generative AI applications using popular development tools and frameworks. NVIDIA NIM enables the integration of pre-trained AI foundation models into products and experiences through simple APIs, significantly increasing developer usage of LLM endpoints and application development frameworks.

NVIDIA was founded by Jensen Huang. It’s NIM microservices provide containers used to self-host GPU-accelerated microservices for pretrained and customized AI models across clouds, data centers, and workstations. These microservices can be deployed with a single command and automatically expose industry-standard APIs for quick integration into applications, development frameworks, and workflows. Key companies involved in this work include Meta, Mistral AI, and Hugging Face, among others.

Accelerating Generative AI Development with NVIDIA NIM

NVIDIA NIM (Neural Infrastructure for Models) is a platform that enables developers and engineering teams to rapidly deploy their own AI model endpoints for the secure development of accelerated generative AI applications. By providing free access to downloadable NIM microservices, NVIDIA aims to simplify the integration of pretrained AI foundation models into products and experiences.

NIM microservices are containers used to self-host GPU-accelerated microservices for pretrained and customized AI models across clouds, data centers, and workstations. These microservices can be deployed with a single command and automatically expose industry-standard APIs for quick integration into applications, development frameworks, and workflows. One example is the OpenAI API specification for large language model (LLM)-based NIM microservices.

Optimized inference engines built with NVIDIA TensorRT and NVIDIA TensorRT-LLM deliver low response latency and high throughput. At runtime, NIM microservices select the optimal inference engine for each combination of foundation model, GPU, and system. NIM containers also provide standard observability data feeds and built-in support for autoscaling with Kubernetes on NVIDIA GPUs.

Simplifying Access to NIM Microservices

To facilitate easier access to NIM for development purposes, NVIDIA is providing free access to downloadable NIM microservices for development, testing, and research to over 5 million NVIDIA Developer Program members. Members of the program are provided comprehensive resources, training, tools, and a community of experts that help build accelerated applications and solutions.

Developer program members can use NIM microservices on up to two nodes or 16 GPUs. When ready to use NIM in production, organizations can sign up for a free 90-day NVIDIA AI Enterprise license. This allows developers to seamlessly transition from development to production environments.

Getting Started with Downloadable NIM Microservices

To get started with downloadable NIM microservices, developers can select a microservice in the NVIDIA API Catalog and choose “Build with this NIM” to download their NIM microservice and obtain an API key for the container. If not yet a program member, developers will have the opportunity to join – just look for the Developer Program option.

For more information, see the Getting Started guide and A Simple Guide to Deploying Generative AI with NVIDIA NIM. Additionally, NVIDIA provides hands-on resources, such as video tutorials, GitHub repo examples, and Colab notebooks, to help developers quickly get started with NIM microservices.

Community Engagement and Resources

To engage with NVIDIA and the NIM microservices community, developers can participate in the NVIDIA NIM developer forum. This platform provides a space for developers to share their experiences, ask questions, and learn from others who are working with NIM microservices.

NVIDIA also offers a range of resources, including video tutorials, GitHub repo examples, and Colab notebooks, to help developers get started with NIM microservices. These resources cover topics such as fine-tuning Llama 3.1 and deploying using NVIDIA NIM directly from a laptop, seamlessly deploying a swarm of LoRA adapters with NVIDIA NIM, and chatting with documents using RAG and NVIDIA AI Workbench.

By providing free access to downloadable NIM microservices and comprehensive resources, NVIDIA aims to accelerate the development of generative AI applications and empower developers to build innovative solutions that transform industries.