.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "gyexamples/plot_qextend_onnxruntime.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        Click :ref:`here <sphx_glr_download_gyexamples_plot_qextend_onnxruntime.py>`
        to download the full example code

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_gyexamples_plot_qextend_onnxruntime.py:


Fast runtime with onnxruntime
=============================

:epkg:`ONNX operators` does not contain operator
from :epkg:`numpy`. There is no operator for
`solve <https://numpy.org/doc/stable/reference/
generated/numpy.linalg.solve.html>`_ but this one
is needed to implement the prediction function
of model :epkg:`NMF`. The converter can be written
including a new ONNX operator but then it requires a
runtime for it to be tested. Example
:ref:`l-extend-python-runtime` shows how to do that
with :epkg:`mlprodict`. Doing the same with
:epkg:`onnxruntime` is more ambitious as it requires
C++...

*to be continued*


.. rst-class:: sphx-glr-timing

   **Total running time of the script:** ( 0 minutes  0.000 seconds)


.. _sphx_glr_download_gyexamples_plot_qextend_onnxruntime.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example


    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: plot_qextend_onnxruntime.py <plot_qextend_onnxruntime.py>`

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: plot_qextend_onnxruntime.ipynb <plot_qextend_onnxruntime.ipynb>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_