onnx_dynamo.rst

TorchDynamo-based ONNX Exporter

.. automodule:: torch.onnx
  :noindex:

• Overview
• Dependencies
• A simple example
• Inspecting the ONNX model using GUI
• When the conversion fails
• API Reference

Warning

The ONNX exporter for TorchDynamo is a rapidly evolving beta technology.

Overview

The ONNX exporter leverages TorchDynamo engine to hook into Python's frame evaluation API and dynamically rewrite its bytecode into an FX Graph. The resulting FX Graph is then polished before it is finally translated into an ONNX graph.

The main advantage of this approach is that the FX graph is captured using bytecode analysis that preserves the dynamic nature of the model instead of using traditional static tracing techniques.

The exporter is designed to be modular and extensible. It is composed of the following components:

• ONNX Exporter: :class:`Exporter` main class that orchestrates the export process.
• ONNX Export Options: :class:`ExportOptions` has a set of options that control the export process.
• ONNX Registry: :class:`OnnxRegistry` is the registry of ONNX operators and functions.
• FX Graph Extractor: :class:`FXGraphExtractor` extracts the FX graph from the PyTorch model.
• Fake Mode: :class:`ONNXFakeContext` is a context manager that enables fake mode for large scale models.
• ONNX Program: :class:`ONNXProgram` is the output of the exporter that contains the exported ONNX graph and diagnostics.
• ONNX Diagnostic Options: :class:`DiagnosticOptions` has a set of options that control the diagnostics emitted by the exporter.

Dependencies

The ONNX exporter depends on extra Python packages:

• ONNX
• ONNX Script

They can be installed through pip:

pip install --upgrade onnx onnxscript

onnxruntime can then be used to execute the model on a large variety of processors.

A simple example

See below a demonstration of exporter API in action with a simple Multilayer Perceptron (MLP) as example:

import torch
import torch.nn as nn

class MLPModel(nn.Module):
  def __init__(self):
      super().__init__()
      self.fc0 = nn.Linear(8, 8, bias=True)
      self.fc1 = nn.Linear(8, 4, bias=True)
      self.fc2 = nn.Linear(4, 2, bias=True)
      self.fc3 = nn.Linear(2, 2, bias=True)

  def forward(self, tensor_x: torch.Tensor):
      tensor_x = self.fc0(tensor_x)
      tensor_x = torch.sigmoid(tensor_x)
      tensor_x = self.fc1(tensor_x)
      tensor_x = torch.sigmoid(tensor_x)
      tensor_x = self.fc2(tensor_x)
      tensor_x = torch.sigmoid(tensor_x)
      output = self.fc3(tensor_x)
      return output

model = MLPModel()
tensor_x = torch.rand((97, 8), dtype=torch.float32)
onnx_program = torch.onnx.export(model, (tensor_x,), dynamo=True)

As the code above shows, all you need is to provide :func:`torch.onnx.export` with an instance of the model and its input. The exporter will then return an instance of :class:`torch.onnx.ONNXProgram` that contains the exported ONNX graph along with extra information.

The in-memory model available through onnx_program.model_proto is an onnx.ModelProto object in compliance with the ONNX IR spec. The ONNX model may then be serialized into a Protobuf file using the :meth:`torch.onnx.ONNXProgram.save` API.

onnx_program.save("mlp.onnx")

Two functions exist to export the model to ONNX based on TorchDynamo engine. They slightly differ in the way they produce the :class:`ExportedProgram`. :func:`torch.onnx.dynamo_export` was introduced with PyTorch 2.1 and :func:`torch.onnx.export` was extended with PyTorch 2.5 to easily switch from TorchScript to TorchDynamo. To call the former function, the last line of the previous example can be replaced by the following one.

onnx_program = torch.onnx.dynamo_export(model, tensor_x)

Inspecting the ONNX model using GUI

You can view the exported model using Netron.

Note that each layer is represented in a rectangular box with a f icon in the top right corner.

By expanding it, the function body is shown.

The function body is a sequence of ONNX operators or other functions.

When the conversion fails

Function :func:`torch.onnx.export` should called a second time with parameter report=True. A markdown report is generated to help the user to resolve the issue.

Function :func:`torch.onnx.dynamo_export` generates a report using 'SARIF' format. ONNX diagnostics goes beyond regular logs through the adoption of Static Analysis Results Interchange Format (aka SARIF) to help users debug and improve their model using a GUI, such as Visual Studio Code's SARIF Viewer.

The main advantages are:

• The diagnostics are emitted in machine parseable Static Analysis Results Interchange Format (SARIF).
• A new clearer, structured way to add new and keep track of diagnostic rules.
• Serve as foundation for more future improvements consuming the diagnostics.

.. toctree::
   :maxdepth: 1
   :caption: ONNX Diagnostic SARIF Rules
   :glob:

   generated/onnx_dynamo_diagnostics_rules/*

API Reference

.. autofunction:: torch.onnx.dynamo_export

.. autoclass:: torch.onnx.ExportOptions
    :members:

.. autofunction:: torch.onnx.enable_fake_mode

.. autoclass:: torch.onnx.ONNXProgram
    :members:

.. autoclass:: torch.onnx.ONNXRuntimeOptions
    :members:

.. autoclass:: torch.onnx.OnnxExporterError
    :members:

.. autoclass:: torch.onnx.OnnxRegistry
    :members:

.. autoclass:: torch.onnx.DiagnosticOptions
    :members: