How-to Python / C++

Getting started

• Command lines
• How to install onnx-light
• Replacing onnxruntime’s protobuf usage with onnx-light
• How to link a C++ project against the pre-built onnx-light artifacts

Model building and I/O

• Build and optimize a graph with GraphBuilder
• How to replace onnx by onnx-light
• How to load and save ONNX files
• How to re-align external weights without loading them in memory
• How to save a model that shares weights with another on-disk model
• How to save and load a model in the ORT flatbuffer format

Testing and benchmarking

• How to collect backend test cases (by op type or by name)
• Run a backend test case with the reference evaluator
• Benchmark methodology

Custom runtime and operators

• How to use a custom kernel
• Persistent input/output feedback
• Quantizes tensors into encoded values
• Tune kernel thresholds
• How to use a custom optim shape inference function
• How to register a built-in kernel, test case, shape inference, light op or peak memory function

Graph rewrites and utilities

• How to add a custom graph-rewriting pattern and set its priority
• How to use ONNX graph manipulation helpers