Issues with ./examples/arm/setup.sh install

[itsMarco-G]

🐛 Describe the bug

Hi Team, I've tried to install executorch on my machine several times in the past and have always encountered some issues.

Here is my flow:
cd executorch #i then check out release v.1.1.0
git submodule sync
git submodule update --init --recursive
python3 -m venv env
source env/bin/activate
pip install -U pip setuptools wheel cmake pytest-cov zstd ninja
./install_executorch.sh --editable
examples/arm/setup.sh --i-agree-to-the-contained-eula

on setup.sh i get an error. I have attached the logs

executorch_arm_setup_20260217_143849.log

` RuntimeError: Failed building reference_model.
[end of output]

note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for tosa-tools

Failed to build tosa-tools
error: failed-wheel-build-for-install

× Failed to build installable wheels for some pyproject.toml based projects
╰─> tosa-tools`

I'm trying to see if codex can help me work around the installation, but after a few attempts i'm still getting errors so i think it's worth raising this issue. If i'm missing something the fix could simply be a ReadMe update.

Versions

Collecting environment information...
PyTorch version: 2.10.0
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A

OS: macOS 15.7.3 (arm64)
GCC version: Could not collect
Clang version: 17.0.0 (clang-1700.0.13.5)
CMake version: version 3.31.10
Libc version: N/A

Python version: 3.10.14 (main, Jul 15 2025, 19:45:59) [Clang 17.0.0 (clang-1700.0.13.5)] (64-bit runtime)
Python platform: macOS-15.7.3-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
Is XPU available: False
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
Caching allocator config: N/A

CPU:
Apple M3 Max

Versions of relevant libraries:
[pip3] executorch==1.1.0a0+17adba1
[pip3] numpy==2.2.6
[pip3] pytorch_tokenizers==1.1.0
[pip3] torch==2.10.0
[pip3] torchao==0.15.0+git9338966da
[pip3] torchaudio==2.10.0
[pip3] torchdata==0.11.0
[pip3] torchsr==1.0.4
[pip3] torchtune==0.6.1
[pip3] torchvision==0.25.0
[conda] numpy 2.2.6 pypi_0 pypi
[conda] torch 2.9.1 pypi_0 pypi
[conda] torchaudio 2.9.1 pypi_0 pypi
[conda] torchvision 0.24.1 pypi_0 pypi

cc @freddan80 @per @zingo @oscarandersson8218 @digantdesai

[zingo]

Hi we merged this fix today that might help
#17486

The tosa team is looking into if it's possible to fix on the older branches also, but you can probably add the line by hand as a workaround temporary. Sorry for the inconvenience 🙏

[itsMarco-G]

Hi @zingo I tried installing fresh again with main (which includes the commit you specified), latest commit being c7c7c0a

i still encountered the same error on step
examples/arm/setup.sh --i-agree-to-the-contained-eula