Edward Chen

Fixed by https://github.com/pytorch/cpuinfo/pull/333.

in microbenchmark measurements, why is blklen 64 asymmetric faster than symmetric? edit: in 3d8fe4d symmetric is faster.

> I believe that [zipmap op ](https://onnx.ai/onnx/operators/onnx_aionnxml_ZipMap.html)outputs map/dictionary not float The Objective-C API doesn't support non-tensor ORTValue types at the moment and ZipMap does not output a tensor. A workaround...

I noticed that this sed command has some of the same text that shows up in the bad URL_HASH value: https://gitlab.archlinux.org/archlinux/packaging/packages/onnxruntime/-/blob/main/PKGBUILD?ref_type=heads#L72-75 Can you verify that the patched cmake/external/onnxruntime_external_deps.cmake file looks...

FYI, I ran into a build failure earlier when I tried this. https://github.com/microsoft/onnxruntime/pull/16618#issuecomment-1648737144

/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...

/azp run Linux OpenVINO CI Pipeline,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,Linux Android Emulator QNN CI Pipeline

/azp run Android CI Pipeline,iOS CI Pipeline,ONNX Runtime React Native CI Pipeline

/azp run Linux QNN CI Pipeline,Win_TRT_Minimal_CUDA_Test_CI,Windows ARM64 QNN CI Pipeline,Windows GPU Doc Gen CI Pipeline

why not add the additional libraries at the time they are used?