[FRONTEND][MXNET 2.0] Support three missing operators: _npi_subtract_scalar, _npi_stack, _npi_advanced_indexing_multiple #6721
Comments
|
Also cc @yzhliu |
|
To provide more context on the |
|
Hey Xingjian, thanks for bringing this up! It is certainly more than welcome for future contribution. Shall we put up a list of MXNet operators to be supported and consolidate them into a single thread instead? If there is no actionable item, shall we close this issue? Thanks! |
|
I think we can create a thread about that. Do you think that we should create a new one? |
|
Yeah we can have a consolidated "[Frontend][MXNet] Importer Missing Operators" thread and mark it as "help wanted". What do you think? |
|
Sounds good to me. Should I change the title of this issue so we may reuse that? (Or create a new one?) |
|
What about creating a new one, categorizing operators like #1799 does |
|
Move to #7186 |
Recently, TVM has supported the incoming MXNet 2.0 frontend via a series of PRs: #6054, #6699. This enables the new GluonNLP 1.0, which has upgraded from MXNet 1.x to MXNet 2.0 to convert to TVM graph (as added in dmlc/gluon-nlp#1390). However, I noticed that there are three missing operators when I profile against the BART model.
The first two operators are pretty straightforward to support while the
_npi_advanced_indexing_multipleis more complicated and is triggered when we calla[idx1, idx2]. The MXNet-side implementation of_npi_advanced_indexing_multipleis here: https://github.com/apache/incubator-mxnet/blob/6bbd53107aa16fc41e8d462cf5dc46fb70d592df/src/operator/numpy/np_indexing_op.cc#L479-L491Since I do not have the bandwidth in supporting this operator. Help is really appreciated.
The text was updated successfully, but these errors were encountered: