masahi opened a new pull request #5306: [Torch] Support Python list, more 
realistic recurrent networks
URL: https://github.com/apache/incubator-tvm/pull/5306
 
 
   This PR builds on the control flow support added in 
https://github.com/apache/incubator-tvm/pull/4964 and aims to support more 
realistic recurrent networks than the simple one in #4964. Specifically the 
goal is to enable translating LSTM models in the PyTorch repo 
https://github.com/pytorch/pytorch/tree/master/benchmarks/fastrnns described in 
[their blog 
post](https://pytorch.org/blog/optimizing-cuda-rnn-with-torchscript/).
   
   Translating these models requires taking care of dynamic lists and tensor 
shape. I added necessary support in the Torch frontend using prelude List ADT, 
static Tensor array https://github.com/apache/incubator-tvm/pull/5103, and Any.
   
   See the new test cases for the kinds of models we can support now. I added 
some variants of LSTMs:
   * LSTM with layer normalization
   * Bidirectional
   * Stacked
   * Stacked and Bidirectional
   
   please review @kevinthesun @zhiics @MarisaKirisame @icemelon9 @jwfromm 
@wweic @alexwong 
   cc @tqchen @jroesch @ajtulloch @junrushao1994 

----------------------------------------------------------------
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.
 
For queries about this service, please contact Infrastructure at:
[email protected]


With regards,
Apache Git Services

Reply via email to