cgerum commented on issue #17543: URL: https://github.com/apache/tvm/issues/17543#issuecomment-2506213968
This error is most likely caused by different cuda versions on the host and device. Please notice that even if tvm is linked against the same cuda versions on the host and the device, it might still be using the wrong `nvcc` command line util. Please make sure that `nvcc --version` give the same results on the host and on the device side. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
