Yi Zhang

Remove temp downloading NDK 25

1

**Description**: Remove the hot fix (downing NDK25) introduced in #12350 **Motivation and Context** - Why is this change required? What problem does it solve? - If it fixes an open...

**Description**: replace deprecated ANDROID_NDK_HOME as ANDROID_NDK_LATEST_HOME **Motivation and Context** Android workflow failed due to deprecated ndk-bundle and retired ANDROID_NDK_HOME

Accelerate Mac CI Workflow with shared cache

2

**Description**: **Motivation and Context** Mac resources in CI is limited and we couldn't scale up or scale out them. There're only 3 threads in Mac agent, so the compilation is...

cuda_version can't be changed in CI. It needs to be improved.

1

## 🐛 Bug In unittest_windows_gpu, there's an environment variable of CUDA_VERSION. https://github.com/pytorch/audio/blob/ecd068f583e4e45ef80635d975ac2bf38d4e819a/.circleci/config.yml.in#L514-L520 But the value couldn't be changed in fact, because it will be revert to 10.2 by regenerate.py https://github.com/pytorch/audio/blob/ecd068f583e4e45ef80635d975ac2bf38d4e819a/.circleci/regenerate.py#L212...

Remove obsolete cuda drivers

1

remove obsolete drivers to avoid potential conflicts. verified link: https://github.com/pytorch/pytorch/pull/75727

conda install unexpected cpu version on Windows

3

## 🐛 Bug conda install cpu version instead of expected cuda version on Windows ## To Reproduce Steps to reproduce the behavior: 1. Run `conda install pytorch torchvision torchaudio cudatoolkit=11.3...

Quantized model test data on GPU

2

# Ask a Question Since the GPU machines of CI have been upgraded from NV6 to T4, it looks quantized model on GPU should be added too. `Hardware support is...

Some Models failed to pass onnxruntime_test_python_symbolic_shape_infer.py

4

# Bug Report ### SSD-MobilenetV1 with opset10 and opset12 call stack ``` FAIL: test_symbolic_shape_infer (__main__.TestSymbolicShapeInference) ---------------------------------------------------------------------- Traceback (most recent call last): File "c:\git\onnxruntime\build\Windows\RelWithDebInfo\RelWithDebInfo\onnxruntime_test_python_symbolic_shape_infer.py", line 47, in test_symbolic_shape_infer SymbolicShapeInference.infer_shapes( File "D:\programs\Continuum\anaconda3\envs\onnxruntime\lib\site-packages\onnxruntime\tools\symbolic_shape_infer.py",...

What's the model name convention?

1

# Ask a Question ### Question Could we remove some characters in the model name. 1. model name contains whitespace https://github.com/onnx/models/blob/e4aa511d91cc4b64f156beb950701b8c744d86a7/ONNX_HUB_MANIFEST.json#L6693 2. model name contains Parentheses https://github.com/onnx/models/blob/e4aa511d91cc4b64f156beb950701b8c744d86a7/ONNX_HUB_MANIFEST.json#L6758 3. model name...

Exception while running bertsquad8 models

1

# Bug Report OS: Windows Run with onnxruntime_test_all.exe Error Message: ``` Invalid Feed Input Name:input1 [ FAILED ] ModelTests/ModelTest.Run/cpu__models_opset8_download_sample_8_bertsquad8, where GetParam() = L"cpu_..\\models\\opset8\\download_sample_8\\bertsquad8.onnx" (917 ms) ``` ### Notes Any additional...