t-vi commented on PR #10758: URL: https://github.com/apache/tvm/pull/10758#issuecomment-1088515266
So some of the tests seem to look at whether cuda is available to torch. We could go over these and avoid that - I'm wondering whether the the `measure_latency` function is used at all btw. https://github.com/apache/tvm/blob/41cfd3d92d1ccd397b76ac45075ccddcf7da6628/tests/python/frontend/pytorch/test_forward.py#L127 Another idea could be to use a CPU-only PyTorch in the build setup and then use a GPU-enabled one in the testing if the problem is mainly with the linkage of libtvm->libtorch->cuda... -- 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]
