Ramakrishnan Sivakumar

Add a link back to the Github page for models under the validated directory

1

The models under the [validated directory](https://github.com/onnx/models/tree/main/validated) show up on the web page like below:  This is not enough information about these models, can we have these model cards have...

Remove skipped models from the webpage

1

Some models had to be skipped because they failed `torch.onnx.verification` . These models have been moved under a folder called skip in each of the following folders: https://github.com/onnx/models/tree/main/Computer_Vision/skip https://github.com/onnx/models/tree/main/Generative_AI/skip https://github.com/onnx/models/tree/main/Natural_Language_Processing/skip...

For now the tests for running onnx.checker and onnxruntime CPU EP were removed from main. Please add new corresponding tests powered by TurnkeyML ASAP to ensure these new models are...

ONNXRuntime failure on models post FP16 conversion through onnxmltools

3

A Pytorch Model converted to onnx using the script below successfully executes through ONNXRuntime. But post FP16 conversion, the model fails with `[ONNXRuntimeError] : 1 : FAIL : Type Error:...

Improve performance of onnx.ai/models

2

ONNX Model Zoo is now accessed through a webpage onnx.ai/models. This webpage is powered by [github pages](https://github.com/onnx/models/tree/gh-pages) that reads the directory strucutre from github.com/onnx/models to populate the webpage. The initial...

Conda env creation is defined [here](https://github.com/onnx/turnkeyml/blob/a998d7a6e4814f0142f3a6937c6ef7fb85428323/src/turnkeyml/run/onnxrt/execute.py#L19). Enhance the methodology to accept requirements and improve exception handling for permission issues.

# Windows Support for Human-Eval This PR adds comprehensive Windows support to the code evaluation pipeline. Here are the key changes: ## Process Management - Replaced Unix-specific `Process` handling with...

We are releasing ONNX 1.18.0. A release branch is created (https://github.com/onnx/onnx/tree/rel-1.18.0). Release candidates are also available from TestPyPI: `pip install -i https://test.pypi.org/simple/ --pre onnx` Updates to op-list and other key...

We are releasing ONNX 1.18.0. A release branch is created (https://github.com/onnx/onnx/tree/rel-1.18.0). Release candidates are also available from TestPyPI: `pip install -i https://test.pypi.org/simple/ --pre onnx` Updates to op-list and other key...

We are releasing ONNX 1.18.0. A release branch is created (https://github.com/onnx/onnx/tree/rel-1.18.0). Release candidates are also available from TestPyPI: `pip install -i https://test.pypi.org/simple/ --pre onnx` Updates to op-list and other key...