masahi commented on pull request #7391: URL: https://github.com/apache/tvm/pull/7391#issuecomment-775469928
I think `reverse` should be done in the frontend, since this seems ONNX specific. For `exclusive`, if you want to avoid the overhead of subtraction, we can do cumsum with exclusive scan. See https://github.com/apache/tvm/blob/1e0d3569b94f650243f4d0ac204d196e3be8b0aa/python/tvm/topi/cuda/scan.py#L517 if `exclusive=True`, we can use `exclusive_scan` instead of `inclusive_scan`. ---------------------------------------------------------------- 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]
