tvm: [Torch] A list of missing op conversion in need of help
Let’s keep a list of missing conversion reported so far in one place here. The list will continue to grow as Torch has too many ops. cc @alexwong @jwfromm @pyjhzwh @jjohnson-arm
Implementing conversion should be straightforward following existing implementations. They are up for grab.
-
aten::reshape -
aten::split -
aten::max_pool1d -
aten::embedding -
prim::ImplicitTensorToNum -
aten::layer_norm -
aten::arange -
aten::rsub -
aten::gelu -
aten::reciprocal -
aten::repeat -
aten::groupnorm
About this issue
- Original URL
- State: closed
- Created 4 years ago
- Comments: 31 (13 by maintainers)
Commits related to this issue
- [PYTORCH]floor_divide support for squeezenet https://github.com/apache/incubator-tvm/issues/5133#issuecomment-636330705 — committed to siju-samuel/tvm by siju-samuel 4 years ago
- [PYTORCH]floor_divide support for squeezenet (#5702) https://github.com/apache/incubator-tvm/issues/5133#issuecomment-636330705 — committed to apache/tvm by siju-samuel 4 years ago
- [PYTORCH]floor_divide support for squeezenet (#5702) https://github.com/apache/incubator-tvm/issues/5133#issuecomment-636330705 — committed to trevor-m/tvm by siju-samuel 4 years ago
- Sync with apache/incubator-tvm 6/15/2020 (#116) * [TFLITE]Select op support for tflite frontend (#5486) * [TFLITE]Select/Where op support for tflite frontend * Review comment fixed * Review ... — committed to neo-ai/tvm by deleted user 4 years ago
- [PYTORCH]floor_divide support for squeezenet (#5702) https://github.com/apache/incubator-tvm/issues/5133#issuecomment-636330705 — committed to trevor-m/tvm by siju-samuel 4 years ago
- [PYTORCH]floor_divide support for squeezenet (#5702) https://github.com/apache/incubator-tvm/issues/5133#issuecomment-636330705 — committed to neo-ai/tvm by siju-samuel 4 years ago
Missing op
aten::copy_:error:
I have encountered the following missing op conversions:
The following operators are not implemented: ['aten::silu_', 'aten::copy_']I’m trying to compile a YoloV5 model in AWS Sagemaker Neo. This is the full failure reason:
ClientError: InputConfiguration: TVM cannot convert the PyTorch model. Invalid model or input-shape mismatch. Make sure that inputs are lexically ordered and of the correct dimensionality. The following operators are not implemented: ['aten::silu_', 'aten::copy_']Is the missing op
aten::im2colandaten::col2imbeing implemented. I saw that #8443 gave up after half of the realization? @masahi Or is there any problem with it？NotImplementedError: The following operators are not implemented: [‘prim::RaiseException’, ‘prim::Uninitialized’, ‘aten::lstm’, ‘aten::_cast_Int’, ‘aten::__derive_index’, ‘aten::not’, ‘aten::tensor’, ‘aten::item’, ‘aten::cast_Float’, ‘prim::data’, ‘aten::format’, 'aten::copy’, ‘aten::append’, ‘aten::FloatImplicit’, ‘prim::dtype’, ‘prim::shape’, ‘prim::TupleIndex’, ‘aten::dim’, ‘aten::warn’, ‘aten::is’, ‘prim::unchecked_cast’]
The model I’m using is from https://github.com/mlperf/inference/tree/master/v0.7/speech_recognition/rnnt/pytorch Pre-trained RNN-T model for MLPerf Inference https://zenodo.org/record/3662521
@megjoshi All ops you requested have been implemented (big thanks to @siju-samuel ), please try again