All Products
Search
Document Center

Platform For AI:Use cases of AI acceleration

Last Updated:Jan 06, 2025

This topic lists use cases of AI acceleration.

Transformer training acceleration

Case

Description

Accelerate the training of transformers

This topic describes how to use PAI-Rapidformer to accelerate the training of PyTorch transformers.

Inference acceleration

Case

Description

Use PAI-Blade to optimize a RetinaNet model that is in the Detectron2 framework

This topic describes how to use PAI-Blade to optimize a RetinaNet model that is in the Detectron2 framework.

Use PAI-Blade and TorchScript custom C++ operators to optimize a RetinaNet model

This topic describes how to use TorchScript custom C++ operators to build the post-processing network of an object detection model and use PAI-Blade to optimize the model.

Use PAI-Blade and TensorRT plug-ins to optimize a RetinaNet model

This topic describes how to use PAI-Blade to optimize a detection model whose post-processing network is built by using TensorRT plug-ins.

Use PAI-Blade to optimize a TensorFlow BERT model

This topic describes how to use PAI-Blade to optimize a TensorFlow BERT model.

Use PAI-Blade to optimize a TensorFlow ResNet50 model

This topic describes how to use PAI-Blade to optimize a TensorFlow ResNet50 model.

Use PAI-Blade to optimize a ResNet50 model with dynamic input shapes

This topic describes how to use PAI-Blade to optimize a ResNet50 model with dynamic input shapes.