hulihan-start opened a new issue, #13782: URL: https://github.com/apache/tvm/issues/13782
I want to evaluator the time cost of tvm, and use the code from https://tvm.apache.org/docs/how_to/optimize_operators/opt_conv_cuda.html?highlight=convolution But I found in my RTX 3090, the time cost is just 5.750624 ms, 10x faster than the results reported by the link. I download tvm from github yesterday and I don't know if there are some errors occured in github project or what codes should I change in my env. Thanks! -- 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]
