Summary: The PyTorch team has introduced a new deep learning compiler called Hidet, which simplifies the process of implementing high-performing deep learning operators on modern accelerators such as NVIDIA GPUs. Hidet can be used as a torch.compile(...) backend to accelerate PyTorch models, making it an attractive option for PyTorch users who want to improve the inference performance of their models, especially for those who also need to implement extremely optimized custom operators. Hidet provides a few options to configure the optimizations, and users can specify hidet as the backend when compiling a model. The article includes a complete example of how to use Hidet to compile and optimize a pre-trained ResNet50 model from torchvision.