Create Dedicated Endpoint from NVIDIA NIM
For enhanced performance and seamless compatibility, NVIDIA-optimized models using NIM container registry are also available on Lepton AI.
In your workspace, select Create from NVIDIA NIM option, you can see a list of available NVIDIA-optimized models.
The NVIDIA-optimized models require an NVIDIA account with access to the NIM container registry. To use those models, you need to have an NVIDIA account with access to the NIM container registry first, and then you can fill in the registry auth key and NGC API key in the deployment creation page.
Select your desired model and fill in the configuration options, click Create to create your dedicated endpoint from NVIDIA NIM.
For more details about the configuration options, checkout the Configuration Options guide.