Runtime, Backend Test, and Kernel Examples#

Examples showing how to retrieve, inspect or run ONNX backend test cases exposed by onnx_light.onnx.backend.

Benchmark Abs: onnxruntime vs onnx-light

Benchmark Abs: onnxruntime vs onnx-light

Benchmark the initialization steps: onnxruntime vs onnx-light

Benchmark the initialization steps: onnxruntime vs onnx-light

Extend ReferenceEvaluator with a custom kernel

Extend ReferenceEvaluator with a custom kernel

Inspect, change, and calibrate kernel tuning from Python

Inspect, change, and calibrate kernel tuning from Python

Profile the runtime memory of a model with the event log

Profile the runtime memory of a model with the event log

Replace a built-in kernel with a Python one and prove it ran

Replace a built-in kernel with a Python one and prove it ran

Retrieve a backend test case and display its model and data

Retrieve a backend test case and display its model and data

Run a model with the runtime and inspect intermediate results

Run a model with the runtime and inspect intermediate results

Run an ONNX model casting a float tensor into an int2 tensor

Run an ONNX model casting a float tensor into an int2 tensor

Run the reference evaluator with tensor, sequence and dictionary inputs/outputs

Run the reference evaluator with tensor, sequence and dictionary inputs/outputs

Gallery generated by Sphinx-Gallery