Technology
Model Compression based on Quantization, Pruning, Knowledge Distillation, and AutoML
Opt-AI’s optimization solution compresses AI models using state-of-the-art techniques
including quantization, pruning, knowledge distillation, and AutoML.
Quantization
Pruning
Knowledge Distillation
Moreover, AI models are accelerated on any target AI chipset including CPUs, GPUs, ASICs and FPGAs,
with the Opt-AI’s hardware-aware automated profiling solution
Inference Speedup
Accuracy Preserving
Hardware Full-Awareness
