How-to Python / C++#
- Command-line interface
- How to install onnx-light
- Build and optimize a graph with GraphBuilder
- How to replace onnx by onnx-light
- Replacing onnxruntime’s protobuf usage with onnx-light
- How to link a C++ project against the pre-built onnx-light artifacts
- 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 a model in the ORT flatbuffer format
- How to collect backend test cases (by op type or by name)
- Run a backend test case with the reference evaluator
- Benchmark methodology
- How to use a custom kernel
- 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
- How to add a custom graph-rewriting pattern and set its priority
- How to use ONNX graph manipulation helpers