Join me for an in-depth livestream on Thursday, July 17 tailored for developers where we unveil how NVIDIA NIM provides everything AI teams need to deploy the latest AI models with a simple ‘docker run’ command.
Date: July 17, 2025
Time: 9 a.m. PT
RSVP: AddEvent
NVIDIA now provides a single NIM container designed to work with the most popular open source LLM architectures, including over 100,000 LLMs on Hugging Face.
With multiple inference backends including NVIDIA TensorRT-LLM, vLLM and SGLang built-in, the LLM-agnostic NIM container automatically pairs your choice of LLM with an optimal inference backend and starts serving it for high performance inference on NVIDIA GPUs anywhere— workstation, datacenter or cloud. Join the Livestream to see how it works including common use-cases and examples demonstrated live.
Read more in our developer blog.
Stay up-to-date with the latest NVIDIA AI announcements by following us on Discord, Instagram, YouTube, and X.