ONNX PyTorch
flytekitplugins-onnxpytorch
This plugin allows you to generate ONNX models from your PyTorch models.
pip install flytekitplugins-onnxpytorchQuick Start(example, may need adjustment)
See full examplespip install flytekitplugins-onnxpytorch
from flytekit import task, workflow
from flytekitplugins.onnxpytorch import PyTorch2ONNX, PyTorch2ONNXConfig
config = PyTorch2ONNX(...)
@task
def my_task() -> None:
...
@workflow
def my_workflow() -> None:
my_task()Available Imports (2)
PyTorch2ONNXConfig is the config used during the pytorch to ONNX conversion.
extends dataclass — configuration or data structure for plugin setup
from flytekitplugins.onnxpytorch import PyTorch2ONNX
PyTorch2ONNXConfig is the config used during the pytorch to ONNX conversion.
extends dataclass — configuration or data structure for plugin setup
from flytekitplugins.onnxpytorch import PyTorch2ONNXConfig
Dependencies
Related Plugins
ONNX TensorFlow
This plugin allows you to generate ONNX models from your TensorFlow Keras models.
ONNX ScikitLearn
This plugin allows you to generate ONNX models from your ScikitLearn models.
Dgxc-lepton
A professional Flytekit plugin that enables seamless deployment and management of AI inference endpoints using Lepton AI infrastructure within Flyte workflows.
Inference
Serve models natively in Flyte tasks using inference providers like NIM, Ollama, and others.