Anerudhan Gopal

Hi @tianleiwu thanks for reporting this. Would you happen to know which MSVC compiler you are using? We do not observe this in our internal CI. Also, confirming this is...

Hi @tianleiwu , I tried updating the MSVC version in our CI-CD but could not reproduce this error. Looking at the [build log from the ONNX MR](https://github.com/microsoft/onnxruntime/actions/runs/8118954587/job/22194111719?pr=19470) that you linked,...

Hi @iskunk , Thanks for reporting this. At this point the UNIT_TESTS are internally being used to test. Hence we do not support that switch publicly. Rather we have tests...

Hi @ZoroDerVonCodier, Graph is a function of the internal nodes (vertices) and tensors (edge) properties. And hence, you are correct to assume the graph is dependent on the shapes of...

Hi, With cudnn frontend `>1.5.2` with cudnn backend `>9.2.0`, the check_support() should be much faster (100x+) improvement. Kindly, let us know if you have more questions Thanks

Can you add which GPU device and cudnn version? A log with `CUDNN_LOGLEVEL_DBG=3` will be useful for debug as well. [https://docs.nvidia.com/deeplearning/cudnn/latest/reference/troubleshooting.html](https://docs.nvidia.com/deeplearning/cudnn/latest/reference/troubleshooting.html)

Hi @ifromeast Is it possible for you to dump the cudnn log? If you set `export CUDNN_LOGLEVEL_DBG=3` and it will dumped to your stdout. The log will look like something...

Could be a driver or toolkit issue. What version of driver are you on? ``` nvidia-smi Mon May 13 08:31:45 2024 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 550.54.14 Driver Version: 550.54.14 CUDA Version:...

Hi @ifromeast, I am still trying to reproduce the issue (Yes I have the latest cudnn-frontend and cudnn). This does not look like a cudnn issue. I suspect this happens...

Hi @simonguozirui , Is it on multi-GPU 4090 as well? Is it possible for you to try two scenarios: a) Try setting CUDA_VISIBLE_DEVICES=0,-1,1 and check if the execution is successful...