Skip to main content
Ctrl+K
onnx-light 0.1.21 documentation - Home onnx-light 0.1.21 documentation - Home
  • Quick tour
  • Start
  • Design
  • API
  • Ops
  • How-To
  • Next Steps
  • Miscellaneous
  • GitHub
  • Quick tour
  • Start
  • Design
  • API
  • Ops
  • How-To
  • Next Steps
  • Miscellaneous
  • GitHub

Section Navigation

ONNX and Concepts

  • Introduction to ONNX
    • ONNX Concepts
    • ONNX with Python
  • Uncompromising Objective
  • Detailed Differences between onnx and onnx_light
  • Proto
    • Protobuf format applied to ONNX
    • ORT flatbuffer format: parallelization and alignment
    • ModelProto creation and no-copy ownership
    • Complex loading and saving scenarios

Library Split

  • How the C++ libraries are split
  • Linking onnx-light in C++

Core

  • Graph building and optimization
    • GraphBuilder
    • Pattern optimization
  • Shape inference
    • Symbolic expression library (onnx_light.onnx_core.expressions)
    • Value-as-shape propagation
    • Symbolic-dimension constraint mechanism
    • Sequences, maps and subgraphs
    • Shape-inference events (ShapeEvent)
    • Shape-inference coverage
  • Runtime Design
    • Processor-aware kernel tuning
    • Buffer-reuse arenas
    • Backend test-case coverage
    • Runtime test coverage (onnxruntime and shape_inference)

Fuzzing

  • Fuzzing
  • Design
  • Proto

Proto#

  • Protobuf format applied to ONNX
  • ORT flatbuffer format: parallelization and alignment
  • ModelProto creation and no-copy ownership
  • Complex loading and saving scenarios

previous

Detailed Differences between onnx and onnx_light

next

Protobuf format applied to ONNX
Show Source

Created using Sphinx 9.1.0.

Built with the PyData Sphinx Theme 0.20.0.