Open gcunhase opened 2 years ago
@gcunhase I don't think we (IBM) have machines executing fp16 on CPU, so we have not exercised this path at this time. We have an accelerator (NNPA) that uses fp16 but we only convert to/from on CPU for exclusive usage on the accelerator. We will probably extend some processing on CPU but we have done so yet at this time.
We would love to have increased type coverage. If you want this support, I believe you will have to contribute support, and we are happy to assist you in this endeavor as well as we can. Testing could be done initially via the lit-tests to ensure that it does what is expected.
How to reproduce
Download
mnist.onnx
model at https://github.com/onnx/onnx-mlir/blob/main/docs/mnist_example/mnist.onnxInstall ONNX-MLIR:
Test that it's working
$ git clone https://github.com/onnx/onnx-mlir.git $ cd onnx-mlir/docker $ python onnx-mlir.py --help
$ pip install onnxmltools
.onnx
to.so
file:Observed behavior
Expected behavior
Generate a
.so
file for the FP16 model.System info
Ubuntu 18.04, Python 3.8 ONNX-MLIR: