Description
🐛 Describe the bug
Hi,
I am doing some work trying to export EfficientSam with XNNPACK backend. I lower the models to CoreML and XNNPACK. I use release 0.4 branch both for lowering and building apple frameworks (./build/build_apple_frameworks.sh). They both work (output sth) when i run them using cpp runners (coreml_executor_runner, xnn_executor_runner). They don't work when i run it in my example app on iOS.
With XNNPACK i get:
ERROR [Error: Failed to run forward on the torch module, error code: 20]
Which i can assume is 0x14 OperatorMissing
(https://github.com/pytorch/executorch/blob/main/runtime/core/error.h)
With CoreML i get:
ERROR [Error: Failed to run forward on the torch module, error code: 18]
Which i can assume is 0x12 InvalidArgument. It used to work on main branch few days ago.
Sorry for no minimal reproducable example for now.
Do you know how can i dig in deeper and diagnose what is not working?
Versions
PyTorch version: 2.5.0
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A
OS: macOS 14.5 (arm64)
GCC version: Could not collect
Clang version: 15.0.0 (clang-1500.3.9.4)
CMake version: version 3.30.5
Libc version: N/A
Python version: 3.10.15 (main, Oct 3 2024, 02:24:49) [Clang 14.0.6 ] (64-bit runtime)
Python platform: macOS-14.5-arm64-arm-64bit
Is CUDA available: False
CUDA runtime version: No CUDA
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: No CUDA
Nvidia driver version: No CUDA
cuDNN version: No CUDA
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Apple M3 Pro
Versions of relevant libraries:
[pip3] executorch==0.4.0a0+6a085ff
[pip3] executorchcoreml==0.0.1
[pip3] numpy==1.26.4
[pip3] torch==2.5.0
[pip3] torchao==0.5.0+git0916b5b
[pip3] torchaudio==2.5.0
[pip3] torchsr==1.0.4
[pip3] torchvision==0.20.0
[conda] executorch 0.4.0a0+6a085ff pypi_0 pypi
[conda] executorchcoreml 0.0.1 pypi_0 pypi
[conda] numpy 1.26.4 pypi_0 pypi
[conda] torch 2.5.0 pypi_0 pypi
[conda] torchaudio 2.5.0 pypi_0 pypi
[conda] torchsr 1.0.4 pypi_0 pypi
[conda] torchvision 0.20.0 pypi_0 pypi