Skip to main content
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The TorchCompileModel node applies PyTorch compilation to a model to optimize its performance. It creates a copy of the input model and wraps it with PyTorch’s compilation functionality using the specified backend. This can improve the model’s execution speed during inference.

Inputs

ParameterData TypeRequiredRangeDescription
modelMODELYes-The model to be compiled and optimized
backendSTRINGYes”inductor"
"cudagraphs”
The PyTorch compilation backend to use for optimization

Outputs

Output NameData TypeDescription
modelMODELThe compiled model with PyTorch compilation applied