The Deci platform enables you to manage, optimize, deploy and serve models in your production environment with ease. You can continue using popular DL frameworks, such as TensorFlow, PyTorch, Keras and ONNX. All you need is our web-based platform or our Python client in order to run it from your code.
Deci provides –
- Performance Acceleration – Accelerate model inference performance by 2x – 10x on any hardware, without compromising accuracy, by using Deci’s Automated Neural Architecture Construction (AutoNAC) technology.
- Scaling on Any Hardware – Cut up to 80% of cloud computation costs and BOM to enable inference at scale, regardless of whether it’s from a private or public cloud, from your own server or from any computer, edge or mobile device.
- Inference Benchmarking – Benchmark your models across any target hardware environment and batch size to find your model’s optimal Throughput, Latency, Memory Usage and Cloud Costs.
- Model Packaging – Quickly and Easily Deploy to Production – Seamlessly deploy trained models from the Deci Lab to any production environment, including all environmental library dependencies in a single encapsulated container.
- Model Serving – Deci’s proprietary deep-learning run-time inference engine can be deployed on your own machine (on any hardware – on-prem / edge / cloud). Deci provides the following options for deploying your Deci Optimized Model as a siloed efficient run-time server–
More information about the Deci platform can be found on the website.
Updated 7 months ago