Acceleration on CPU

Whisper optimization with PTQ and pre/post processing

BERT optimization with Intel® Neural Compressor Post Training Quantization

BERT optimization with QAT Customized Training Loop

ResNet optimization with QAT Default Training Loop

ResNet optimization with QAT PyTorch Lightning Module

Cifar10 optimization with OpenVINO for Intel HW

Acceleration on GPU

Bert optimization with CUDA/TensorRT

SqueezeNet latency optimization with DirectML

Stable Diffusion optimization with DirectML

Dolly V2 optimization with DirectML

Acceleration on NPU

Inception model optimization on Qualcomm NPU

Acceleration on DPU

ResNet optimization with Vitis-AI Post Training Quantization for AMD DPU