Is it currently possible to deploy our own models on NVIDIA's cloud and use NIM for inference?

Currently, there are many AI networks on the NIM website that can be used for inference directly through HTTP requests, like llama3-70b-instruct, stable-diffusion-3-medium, etc. I would like to ask if it is possible to deploy our own networks and pretrained models on NVIDIA’s cloud in the same way as those models, and use HTTP requests to perform inference from anywhere.

Hi @901228 – at the moment, we don’t have the ability for users to deploy their own models on the API Catalog. Are there any particular pre-trained models you’d be interested in?

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.