?Automatic benchmark of inference performance across multiple models, hardware types and batch sizes.
?Seamless inference optimization by automatically applying techniques such as weights quantization and graph compilation.
AutoNAC Inference Optimization
Optimized Model Usage
?The maximum number of deep learning models you can use/download out of those optimized in the platform.
?The inference hardware. Deci’s optimization is hardware-aware. It means that our technology can squeeze the maximum utilization out of the hardware targeted for inference in production.
?The deep learning development frameworks that are supported.
Deployment and Serving Options
?The inference server module that can run Deci platform models.
?API access for easy integration with your existing tools and CI/CD processes.
?The platform is hosted on Deci’s servers. We offer an on-prem deployment for enterprises.
Support & SLA