Automating Optimization of Quantized Deep Learning Models on CUDA

In emerging models such as ResNeXt and Deformable ConvNets, the automatic optimization makes it easy for TVM to adapt to these new workloads and achieve a significant performance boost. TVM provides an easy workflow to quantize trained models from other frameworks, automatically optimize operators (with AutoTVM), and deploy to different devices. We also benchmark on DRN-C-26, ResNeXt-50, and DCN-ResNet-101 from Deformable ConvNets to show the performance of emerging models, which contains less conventional operators such as dilated convolutions, group convolutions and deformable convolutions.

Source: tvm.ai