AI Model Optimization based on Compression and AutoML

Opt-AI’s optimization compresses AI models using state-of-the-art techniques including quantization,
pruning, knowledge distillation, and AutoML for the edge and the cloud. Moreover,

AI models are accelerated on any other target hardware including
CPUs, GPUs, ASICs and FPGAs, with the hardware-aware automated quantization.

❏ Quantization

❏ Pruning

❏ Knowledge distillaion

Main Advantages

Inference Speedup

Accuracy Preserving

Hardware Full-Awareness

Model size & memory reduction

AI Optimization Platform