masahi commented on issue #6268: URL: https://github.com/apache/incubator-tvm/issues/6268#issuecomment-690031948
@t-vi to be clear, @nolanliou's problem is not about div op being applied to integers (it is another story), the same error would happen if it is add or mul. `torch.result_type` is confused with one of the inputs being numpy scalar of type np.int64, and it returns float32 when both lhs and rhs are clearly int64. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected]
