Speed up your models with minimal code changes using torch.compile, the latest PyTorch compiler solution.

Model-Optimization,torch.compile

An example of applying torch.compile to a real model, demonstrating speedups.

Model-Optimization,torch.compile

Learn how to use compiled autograd to capture a larger backward graph.

Model-Optimization,CUDA,torch.compile

Learn the usage, debugging and performance profiling for ``torch.compile`` with Inductor CPU backend.

Model-Optimization,torch.compile

Learn how to use torch.compiler.set_stance

Model-Optimization,torch.compile

Learn how to export models for popular usecases

Model-Optimization,torch.compile

Speed up the optimizer using torch.compile

Model-Optimization,torch.compile

Speed up training with LRScheduler and torch.compiled optimizer

Model-Optimization,torch.compile

Learn how to use user-defined kernels with ``torch.compile``

Model-Optimization,torch.compile

Learn how to use compile time caching in ``torch.compile``

Model-Optimization,torch.compile

Learn how to configure compile time caching in ``torch.compile``

Model-Optimization,torch.compile

Learn how to use regional compilation to control cold start compile time

Model-Optimization,torch.compile

Learn an end-to-end example of how to use AOTInductor for python runtime.

Basics,torch.export

Learn how to use torch.export to export PyTorch models into standardized model representations.

Basics,torch.export

Build a image classifier model in PyTorch and convert it to ONNX before deploying it with ONNX Runtime.

Production,ONNX,Backends

Demonstrate end-to-end how to address unsupported operators in ONNX.

Production,ONNX,Backends

Demonstrate how to handle control flow logic while exporting a PyTorch model to ONNX.

Production,ONNX,Backends

Build a simple FX pass that fuses batch norm into convolution to improve performance during inference.

FX

Build a simple FX interpreter to record the runtime of op, module, and function calls and report statistics

FX