thaisacs commented on issue #17276: URL: https://github.com/apache/tvm/issues/17276#issuecomment-2323443553
Hi, @SerodioJ In your scripts, you put data_tvm instead of data. Note that this does not seem to be a TVM issue. It is normal for the float precision to change on different architectures (NumPy only runs on CPUs). Note that for GPU, https://tvm.d2l.ai/chapter_gpu_schedules/vector_add.html#cuda-programming, they use mxnet as a baseline. This might be interesting: https://www.geeksforgeeks.org/python-cupy/. Regards, Thais. -- 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]
