vvchernov opened a new pull request #8583: URL: https://github.com/apache/tvm/pull/8583
The main aim of the patch to reduce time of testing of different modifications of LSTM layer implemented in pytorch frontend. The following changings were done: 1. Reduce input sequence size and batch size. Also other sizes was changed, they are taken from lstm test for onnx frontend 2. Skip LSTM modification with projection. It is rare used and supported by pytorch framework only 3. Skip tests which check onnx model LSTM modifications converted from pytorch model For points 2 and 3: the code was not removed, the paths to it were commented only. It can be switch in the future if need @masahi please review this patch -- 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]
