Bowen Bao
Bowen Bao
Please checkout CI failure
Thanks for the suggestion @yan12125, that helped! I'm now getting the below failure ``` onnxoptimizer/examples/onnx_optimizer_exec.cpp:15:24: error: ‘class onnx::ModelProto’ has no member named ‘ParseFromIstream’; did you mean ‘ParseFromString’? bool success =...
Hi @xadupre is the PR ready to be merged?
> No, the bug is still here. When the model is unpickled, xgboost does not restore exactly the same object and the converter does not find one attribute it is...
> > > Thanks for your issue! > > What are "split_predict" and "lift_lexical_references" used for? I thought they are legacy passes and only useful for the caffe2 backend. Please...
@tianleiwu thanks for following up. I have created a simple initial version for helping Ye with the implementation. Will create a PR afterwards.
PR work in progress. https://github.com/microsoft/onnxruntime/pull/11629
Getting `Failed to find nvToolsExt` error on windows with cuda 11.8 after this commit. Maybe it has to do with the newer cuda version I'm using. Builds successfully after reverting.
@peterbell10 ``` > dir env: | grep NVTOOLS NVTOOLSEXT_PATH C:\Program Files\NVIDIA Corporation\NvToolsExt\ ```
@peterbell10 the issue seems to be around https://github.com/pytorch/pytorch/blob/961e05245c47219800fd55b8da035ae7dcbe564b/cmake/Modules/FindCUDAToolkit.cmake#L1045-L1055. The log where I set `NVTOOLSEXT_PATH` in my environment ``` CMake Debug Log at cmake/Modules/FindCUDAToolkit.cmake:1050 (find_path): find_path called with the following settings:...