How to Deploy NVIDIA NIM in 5 Minutes

Описание: NVIDIA NIM is a set of microservices for deploying AI models. Tap into the latest AI foundation models—like Stable Diffusion, esmfold, and Llama 3—with downloadable NIM microservices for your application deployment.

Join Neal Vaidya, developer advocate at NVIDIA, for a demo on how to quickly deploy NVIDIA NIM microservices, locally with Python or programmatically through Docker. This tutorial focuses on deploying Llama 3.

0:22 - Overview of NIM microservices (https://nvda.ws/4bZLY9E)
0:36 - Test the Llama 3 model on a web browser with a hosted API
0:51 - Generate an API key and get sample code snippets
0:59 - Test the Llama 3 model in a self-hosted environment
1:08 - Get access to API catalog to begin self-hosted deployment
1:22 - Pre-install Docker engine and Docker CLI tool
1:50 - Authenticate your container
1:55 - Generate an environment variable called NGC API key
2:05 - Input a single Docker run command
2:19 - Expose Docker to all GPUs to the running container
2:28 - Expose the API environment variable
2:35 - Mount the cache to download and store model weights
2:48 - Specify the NIM should run as a local user
2:53 - Expose the main port to interact with the running NIM
3:03 - Add the model name to the image path
3:30 - Confirm the service is ready in another terminal using curl
3:41 - Send the container a new request

Developer resources:

▫️ Learn more about NIM: https://nvda.ws/3yqsuNw
▫️ Join the NVIDIA Developer Program: https://nvda.ws/3OhiXfl
▫️ Access downloadable NIM microservices on the API catalog: https://nvda.ws/4bZLY9E
▫️ Read the Mastering LLM Techniques series to learn about inference optimization, LLM training, and more: https://resources.nvidia.com/en-us-la...



#inferencemicroservices #inferenceoptimization #api #selfhosting #modeldeployment #aimodel #LLM #generativeai #aimicroservices #nvidianim #generativeaideployment #aiinference #productiongenai #enterprisegenerativeai #acceleratedinference #nvidiaai #apicatalog