Hello,
I have written a simple program to run some vision models from HuggingFace in this gist: https://gist.github.com/oluwatimilehin/db204bcab6eb7531173453a2e4ed7e8e.
However, I cannot run the segformer model using python vision_models.py -m segformer -b 1, as I get a NotImplementedError: Not supporting format message.
I've tracked the error down to this line:
|
raise NotImplementedError("Not supporting format") |
Which gets invoked when it receives an arg (d1//128) with type FloorDiv.
I'm not flagging this as a bug, as you document that it's unsupported, but I'm creating an issue to track this just for awareness.
Hello,
I have written a simple program to run some vision models from HuggingFace in this gist: https://gist.github.com/oluwatimilehin/db204bcab6eb7531173453a2e4ed7e8e.
However, I cannot run the segformer model using
python vision_models.py -m segformer -b 1, as I get aNotImplementedError: Not supporting formatmessage.I've tracked the error down to this line:
PyTorchSim/PyTorchSimFrontend/mlir/mlir_codegen_backend.py
Line 836 in 509f425
Which gets invoked when it receives an arg
(d1//128)with typeFloorDiv.I'm not flagging this as a bug, as you document that it's unsupported, but I'm creating an issue to track this just for awareness.