Welcome to the NVIDIA® NIM™ Bootcamp! The bootcamp helps developers get started with NVIDIA® NIM™ microservices by building real-world generative AI (GenAI) applications. The labs guide participants through setting up NIM Docker containers and utilizing REST API endpoints for serving inference requests. Additionally, attendees will explore fine-tuning models using Parameter Efficient Fine-Tuning (PEFT) techniques such as Low-Rank Adaptation (LoRA) using single and multi-gpu training strategies, with hands-on experience in fine-tuning adapters for the LLaMA-3 8B model. Participants will also utilise multimodal NIM and put multiple NIM in agentic workflows using LangGraph. The bootcamp gives a hands-on overview of deploying NIM Blueprints.
This content contains 6 Labs, plus an optional LoRA finetuning notebook:
- Lab 1: Building RAG via NVIDIA NIM APIs
- Lab 2: Building RAG with a Localized NVIDIA NIM
- Lab 3: Running NVIDIA NIM with LoRA Adapters
- [Optional Notebook] Training own adapters on custom datasets using single-GPU and multi-GPU strategies
- Lab 4: Multimodal NIM (VLM)
- Lab 5: Utilising NVIDIA NIM as Agents
- Lab 6: NVIDIA NIM Blueprints
The tools and frameworks used in the Bootcamp material are as follows:
The total Bootcamp material would take approximately 6 hours and 30 minutes.
To deploy the Labs, please refer to the deployment guide presented here
This material originates from the OpenHackathons Github repository. Check out additional materials here
Don't forget to check out additional Open Hackathons Resources and join our OpenACC and Hackathons Slack Channel to share your experience and get more help from the community.
Copyright © 2025 OpenACC-Standard.org. This material is released by OpenACC-Standard.org, in collaboration with NVIDIA Corporation, under the Creative Commons Attribution 4.0 International (CC BY 4.0). These materials may include references to hardware and software developed by other entities; all applicable licensing and copyrights apply.