George Wu

Results 54 comments of George Wu
trafficstars

@ryanunderhill , any idea why onnxruntime_providers_shared isn't created on MacOS? It should be supported for all platforms?

+@sfatimar , @preetha-intel I recall that OpenVINO EP explicitly did not support MacOS. perhaps it is time to revisit since native OpenVINO does support it?

> @jywu-msft @jcwchen 😢 Still not building on Arm: > > ``` > running build_ext > running cmake_build > Using cmake args: ['C:\\Users\\gkhmyznikov\\AppData\\Local\\Temp\\pip-build-env-fboe5om8\\overlay\\Scripts\\cmake.EXE', '-DPYTHON_INCLUDE_DIR=C:\\Users\\gkhmyznikov\\AppData\\Local\\Programs\\Python\\Python311-arm64\\Include', '-DPYTHON_EXECUTABLE=X:\\Github\\PWABuilder\\Windows-DevRel\\Tools\\ML-tests\\.temp\\env_onnx\\Scripts\\python.exe', '-DBUILD_ONNX_PYTHON=ON', '-DCMAKE_EXPORT_COMPILE_COMMANDS=ON', '-DONNX_NAMESPACE=onnx', '-DPY_EXT_SUFFIX=.cp311-win_arm64.pyd', '-DCMAKE_BUILD_TYPE=Release',...

/azp run Linux OpenVINO CI Pipeline

/azp run Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-amd-gpu-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,onnxruntime-binary-size-checks-ci-pipeline,Big Models,Android CI Pipeline, Linux Android Emulator QNN CI Pipeline

/azp run Linux OpenVINO CI Pipeline

/azp run Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-amd-gpu-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,onnxruntime-binary-size-checks-ci-pipeline,Big Models,Android CI Pipeline, Linux Android Emulator QNN CI Pipeline

/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows CPU CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline,ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline,Linux CPU Minimal...

> @jywu-msft Could you please review these build changes ? They enable a compile of the TRT EP without any other cuda dependencies other than cudart. sorry I missed this....

it it runs on SM8550 but fails on SM8350 , it's unlikely to be an onnxruntime EP issue. the error typically happens when QNN op validation fails (and because the...