Skip to main content
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

ParameterDescriptionData TypeRequiredRange
modelThe model to be compiled and optimizedMODELYes-
backendThe PyTorch compilation backend to use for optimization (default: “inductor”)STRINGYes”inductor"
"cudagraphs”

Outputs

Output NameDescriptionData Type
modelThe compiled model with PyTorch compilation appliedMODEL
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 240c6eb84ce2b93fe4d7c04fcf69df571e662f17893a4fd8e721241ea082edc8