ymwangg commented on pull request #8440: URL: https://github.com/apache/tvm/pull/8440#issuecomment-877544167
@comaniac Thanks for the valuable comments. I found the Pytorch implementation https://github.com/apache/tvm/blob/main/python/tvm/relay/frontend/pytorch.py#L1624 cannot handle dynamic shapes. So I added this optimization based on the ONNX implementation. For some reason, the weight matrix of nn.dense must be static for the tvm codegen to work correctly, though using libs like mkl works just fine. I created an issue for this https://github.com/apache/tvm/issues/8441. -- 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]
