NGC | Catalog
Welcome Guest
CatalogResourcesResNeXt101-32x4d Triton deployment for PyTorch

ResNeXt101-32x4d Triton deployment for PyTorch

For downloads and more information, please view on a desktop device.
Logo for ResNeXt101-32x4d Triton deployment for PyTorch


Deploying high-performance inference for ResNeXt101-32x4d model using NVIDIA Triton Inference Server.



Use Case




Latest Version



November 12, 2021

Compressed Size

0 B

This resource is a subproject of resnext_for_pytorch. Visit the parent project to download the code and get more information about the setup.

The ResNeXt101-32x4d is a model introduced in the Aggregated Residual Transformations for Deep Neural Networks paper. It is based on regular ResNet model, substituting 3x3 convolutions inside the bottleneck block for 3x3 grouped convolutions.

The ResNeXt101-32x4d model can be deployed for inference on the NVIDIA Triton Inference Server using TorchScript, ONNX Runtime or TensorRT as an execution backend.