Compilation#
How Torch-TensorRT compiles models: the JIT torch.compile path, the AOT
torch.export path, compilation settings, and dynamic shape configuration.
- TensorRT Backend for
torch.compile - Example: Torch Compile Advanced Usage
- Compiling Exported Programs with Torch-TensorRT
- CompilationSettings Reference
- Dynamic shapes with Torch-TensorRT
- Example: Compiling Models with Dynamic Input Shapes
- Example: Sharing Dynamic Dimensions Across Inputs
- Handling Unsupported Operators