ah-cheng opened a new pull request, #11242: URL: https://github.com/apache/tvm/pull/11242
When I import onnx model. I ran into a bug with matmul. The matmul input shape is: a:[1,1,31,64,16], b:[3,31,64,16]. Thus the broadcast shape should be [1,3,31,64,16]. the both inputs should broadcast. So far our code just handld the case of one input broadcast. So I fix it. Thanks to help reviews. CC: @AndrewZhaoLuo -- 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]
