Welcome to the NVIDIA NIM Bootcamp! This hands-on learning experience is designed to empower developers with practical skills in building production-ready Generative AI applications using NVIDIA NIM™. Through this bootcamp, the attendees dive into real-world application of building a Retrieval Augmented Generation (RAG) in both cloud-based and local deployment scenarios. The comprehensive labs will guide you through:
- Setting up and operationalising NIM Docker containers
- Implementing and consuming REST API endpoints for inference
- Building an end-to-end RAG application
- Exploring Parameter Efficient Fine-Tuning (PEFT) techniques
- Training and deploying custom Low-Rank Adaptation (LoRA) models
- Fine-tuning adapters for state-of-the-art models like LLaMA-3 8B
This content contains three 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
- Application of NIM Blueprints (coming soon)
The tools and frameworks used in the Bootcamp material are as follows:
The total Bootcamp material would take approximately 3 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.