leandron commented on PR #16653: URL: https://github.com/apache/tvm/pull/16653#issuecomment-1976476946
> Hello Leandron(@leandron), I understand your concerns, but TVM currently does not support reading quantized models from Paddle. Therefore, the Softmax operator cannot yet be offloaded to CMSIS-NN. I am working on adding support for TVM to handle Paddle's quantized models. I plan to add this test after the successful merge of [TVM PR 16651](https://github.com/apache/tvm/pull/16651). Sure, so let's get 16651 merged, and then update this one with a test case, then we merge this. -- 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]
