Contents Menu Expand Light mode Dark mode Auto light/dark mode
onnx-array-api 0.1.3 documentation
Logo
onnx-array-api 0.1.3 documentation

Contents

  • Tutorial
    • Many ways to implement a custom graph in ONNX
    • Light API for ONNX: everything in one line
    • Numpy API for ONNX
      • First examples with onnx-array-api
      • First examples with onnxruntime
    • Benchmarks
      • Benchmark of TreeEnsemble implementation
  • API
    • onnx_array_api.array_api
      • onnx_array_api.array_api.onnx_numpy
      • onnx_array_api.array_api.onnx_ort
      • onnx_array_api.npx.npx_array_api
    • onnx_array_api.light_api
    • npx_core_api
    • npx.npx_functions
    • npx_jit_eager
    • npx.npx_numpy_tensors
    • npx_tensors
    • npx.npx_types
    • Shortcuts
    • npx.npx_var
    • onnx tools
    • ort
    • plotting
    • reference
    • tools
    • profiling
    • Float 8
    • validation.docs
  • Technical Details
    • Difficulty to implement an Array API for ONNX
  • Example gallery
    • About float 8
    • First examples with onnx-array-api
    • First examples with onnxruntime
    • Optimization with onnxruntime
    • Profiling with onnxruntime
    • Benchmark of TreeEnsemble implementation

More

  • Change Logs
  • License
Back to top

Example gallery#

A couple of examples to illustrate different implementation of dot product (see also sphinx-gallery).

About float 8

About float 8

First examples with onnx-array-api

First examples with onnx-array-api

First examples with onnxruntime

First examples with onnxruntime

Optimization with onnxruntime

Optimization with onnxruntime

Profiling with onnxruntime

Profiling with onnxruntime

Benchmark of TreeEnsemble implementation

Benchmark of TreeEnsemble implementation

Download all examples in Python source code: auto_examples_python.zip

Download all examples in Jupyter notebooks: auto_examples_jupyter.zip

Gallery generated by Sphinx-Gallery

Next
About float 8
Previous
Difficulty to implement an Array API for ONNX
Copyright © 2023, Xavier Dupré
Made with Sphinx and @pradyunsg's Furo