Nvidia Courses

Setting Up a RAG Demo on NVIDIA AI Workbench - Step-by-Step Tutorial

Step-by-step guide to set up a retrieval-augmented generation (RAG) system using NVIDIA AI Workbench, enabling developers to create AI projects on their local machines without a GPU in about an hour.

• YouTube
• 25 minutes
• Self-Paced
• Free Video

Building an AI-Enabled Network Video Recorder with NVIDIA Metropolis Microservices for Jetson

Learn to build an AI-enabled Network Video Recorder using NVIDIA Metropolis microservices for Jetson. Covers system setup, microservices, diagnostics, and code samples for various operations in edge AI applications.

• YouTube
• 23 minutes
• Self-Paced
• Free Video

Fine-tuning Character Animation with Autodesk Maya and NVIDIA ACE

Adjust settings in Autodesk Maya to fine-tune character animation, focusing on personality, reactions, and facial movements using NVIDIA ACE technology.

• YouTube
• 12 minutes
• Self-Paced
• Free Video

1001 Ways to Write CUDA Kernels in Python

Explore best practices for writing CUDA kernels in Python, covering memory management, thread organization, and optimization techniques to harness GPU acceleration without leaving the Python ecosystem.

• YouTube
• 38 minutes
• Self-Paced
• Free Video

How Math Libraries Can Help Accelerate Your Applications on Blackwell GPUs

Discover how NVIDIA's GPU-accelerated math libraries in the CUDA Toolkit and HPC SDK can optimize performance for AI, ML, and scientific computing workflows on Blackwell GPUs.

• YouTube
• 44 minutes
• Self-Paced
• Free Video

A Deep Dive Into the Latest HPC Software

Dive into the latest developments in NVIDIA software for high performance computing, covering programming models, compilers, libraries, and tools for HPC applications, quantum computing, and scientific visualization.

• YouTube
• 34 minutes
• Self-Paced
• Free Video

Introducing NVIDIA Dynamo: A Distributed Inference Serving Framework for Reasoning Models

Discover NVIDIA Dynamo, a distributed inference serving framework for reasoning LLMs in multi-node environments, featuring disaggregated serving techniques and seamless scaling capabilities for optimized request handling.

• YouTube
• 1 hour 29 minutes
• Self-Paced
• Free Video

The New PyTorch Architecture for TensorRT-LLM

Explore NVIDIA's new PyTorch-based architecture for TensorRT-LLM, enhancing user experience and developer velocity for custom LLM deployments while delivering state-of-the-art performance on NVIDIA GPUs.

• YouTube
• 52 minutes
• Self-Paced
• Free Video

Customizing AI Agents for Tool Calling with NVIDIA NeMo Microservices

Master the process of customizing AI agents for tool calling using NVIDIA NeMo microservices through this end-to-end tutorial covering data preparation, LoRA fine-tuning, model evaluation, and implementing guardrails.

• YouTube
• 14 minutes
• Self-Paced
• Free Video

Advanced Multi-GPU Scaling: Communication Libraries

Discover how to scale applications beyond single GPU limitations using CUDA-aware MPI, NVSHMEM, and NCCL, demonstrated through real-world examples for computing larger workloads faster.

• YouTube
• 42 minutes
• Self-Paced
• Free Video

What Is Trustworthy AI?

Discover how NVIDIA is building a better world through Trustworthy AI, focusing on privacy, safety, transparency, and reducing bias in AI systems.

• YouTube
• 13 minutes
• Self-Paced
• Free Video

Deploying Generative AI Applications - Building Code Assistants, Image Search, and Robotics Solutions

Discover practical implementations of LLMs through hands-on demonstrations of image search applications, coding assistance tools, and vision-language action models for robotics integration.

• YouTube
• 11 minutes
• Self-Paced
• Free Video

Step by Step Installation of NVIDIA Virtual GPU on Windows Server 2025

Master NVIDIA Virtual GPU installation on Windows Server 2025 with step-by-step guidance covering Hyper-V setup, vGPU Manager installation, GPU partitioning, and driver setup for both Windows and Linux.

• YouTube
• 24 minutes
• Self-Paced
• Free Video

10 Lines of Code - Data Science Agent

Learn to build a data science agent using just 10 lines of code through this hands-on tutorial that demonstrates the complete process in a Google Colab notebook. Follow a structured 5-step approach that begins with setting up Colab, configuring GPU acces…

• YouTube
• 26 minutes
• Self-Paced
• Free Video

3 Ways to Accelerate Pandas with NVIDIA GPUs

Discover 3 no-code and low-code methods to accelerate pandas operations using NVIDIA GPUs, from magic commands to cuDF integration for faster data processing.

• YouTube
• 10 minutes
• Self-Paced
• Free Video