Free Hands-On Labs

Get Started with Inference

Kick-start your AI inference journey with immediate, short-term access to NVIDIA Triton and NVIDIA TensorRT—for free.

Experience Accelerated Inference

In these hands-on labs, you’ll experience fast and scalable AI using NVIDIA Triton™ Inference Server, platform-agnostic inference serving software, and NVIDIA TensorRT™, an SDK for high-performance deep learning inference that includes an inference optimizer and runtime. You’ll be able to immediately unlock the benefits of NVIDIA’s accelerated computing infrastructure and scale your AI workloads. Choose one below to get started and ask NVIDIA experts questions about your specific infrastructure.

Choose Your Desired Lab to Get Started

View all of the hands-on labs available through NVIDIA LaunchPad that include Inference below.

Spear Phishing Detection using Generative AI

Spear Phishing Detection using Generative AI

Best for: AI practitioner

Included products: NVIDIA AI Enterprise, NVIDIA Morpheus, NVIDIA-Certified Systems

Included technologies: Cyber Log Accelerators, NVIDIA Cloud-Native, NVIDIA RAPIDS, NVIDIA TensorRT, NVIDIA Triton Inference Server

Route Optimization

Route Optimization

Best for: AI practitioner, Developer

Included products: NVIDIA AI Enterprise, NVIDIA cuOpt, NVIDIA-Certified Systems

Included technologies: NVIDIA cuOpt Server APIs, NVIDIA Cloud-Native

AI Chatbot with Retrieval Augmented Generation

AI Chatbot with Retrieval Augmented Generation

Best for: AI practitioner, Developer

Included products: NVIDIA AI Enterprise, NVIDIA-Certified Systems

Included technologies: Large Language Models (LLMs), NVIDIA Cloud-Native, NVIDIA NeMo, NVIDIA TensorRT, NVIDIA TensorRT-LLM, NVIDIA Triton Inference Server, Retrieval Augmented Generation (RAG)

Digital Fingerprinting to Detect Cyber Threats

Digital Fingerprinting to Detect Cyber Threats

Best for: AI practitioner

Included products: NVIDIA AI Enterprise, NVIDIA Morpheus, NVIDIA-Certified Systems

Included technologies: Cyber Log Accelerators, NVIDIA Cloud-Native, NVIDIA RAPIDS, NVIDIA Triton Inference Server, TensorRT

Accelerated Computing and AI with Grace Hopper

Accelerated Computing and AI with Grace Hopper

Best for: AI practitioner, Data engineer, Data scientist, Developer

Included products: NVIDIA GH200 Grace Hopper Superchip

Included technologies: BERT, Large Language Models (LLMs), NVIDIA NeMo, NVIDIA TensorRT, NVIDIA Triton Inference Server

5 Minutes to Generative AI Inference

5 Minutes to Generative AI Inference

Best for: AI practitioner, Developer

Included products: NVIDIA AI Enterprise, NVIDIA-Certified Systems

Each lab comes with world-class service and support.

Here’s What You Can Expect From NVIDIA LaunchPad Labs

A Hands-On Experience

A Hands-On Experience

Take curated labs that walk you through the entire process, from infrastructure optimization to application deployment.

Ready-to-Use Infrastructure

Ready-to-Use Infrastructure

Test and prototype on ready-to-use infrastructure that’s hosted at Equinix and available to you.

Assistance From Experts

Assistance From Experts

Learn from documented, self-paced experiences and access assistance from NVIDIA experts when you need it.

Confident Design and Purchase Decisions.

Confident Design and Purchase Decisions.

After using NVIDIA LaunchPad, you’ll make more confident design and purchase decisions to accelerate your journey.

Choose a lab from above to get immediate access.