Deploy: Standardized Runtime for Your Edge Devices
Latent Runtime Engine is a secure, standardized runtime engine for Edge AI that is frictionless to deploy and maintain.
Easy to install
Standardized runtime portable to multiple hardware platforms.
Update or replace model with no changes to your runtime engine.
Lightweight engine for all LEIP services and inference.
Compatible with C++ and Python.
APIs for easy third-party and application integration.
Portable to hardware of your choice
Support for NVIDIA Jetson Orin and Xavier
Android Snapdragon
CUDA, ARM, and x86 running Linux
Safeguard and monitor your model
Deter unauthorized use or distribution of models with digital watermarks.
Protect models from theft or compromise with an encrypted runtime.
Seamlessly measure performance during deployment with real-time diagnostic metrics.