No module named 'tosa' using executorch==0.7

🐛 Describe the bug

I installed executorch==0.7 by pip install, and when I run example code in https://docs.pytorch.org/executorch/stable/getting-started.html ,

from executorch.backends.arm.ethosu_partitioner import EthosUPartitioner

it raised the bug:

File ***/envs/vela/lib/python3.12/site-packages/executorch/backends/arm/tosa_quant_utils.py:23
     21 from torch import Tensor
     22 from torch.fx import Node
---> 23 from tosa.RoundingMode import RoundingMode  # type: ignore
     26 q_ops = (
     27     exir_ops.edge.quantized_decomposed.quantize_per_tensor.default,
     28     exir_ops.edge.quantized_decomposed.quantize_per_channel.default,
     29 )
     30 dq_ops = (
     31     exir_ops.edge.quantized_decomposed.dequantize_per_tensor.default,
     32     exir_ops.edge.quantized_decomposed.dequantize_per_channel.default,
     33 )

ModuleNotFoundError: No module named 'tosa'

Versions

Versions of relevant libraries:
[pip3] executorch==0.7.0
[pip3] numpy==2.3.2
[pip3] nvidia-cublas-cu12==12.8.4.1
[pip3] nvidia-cuda-cupti-cu12==12.8.90
[pip3] nvidia-cuda-nvrtc-cu12==12.8.93
[pip3] nvidia-cuda-runtime-cu12==12.8.90
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cufft-cu12==11.3.3.83
[pip3] nvidia-curand-cu12==10.3.9.90
[pip3] nvidia-cusolver-cu12==11.7.3.90
[pip3] nvidia-cusparse-cu12==12.5.8.93
[pip3] nvidia-cusparselt-cu12==0.7.1
[pip3] nvidia-nccl-cu12==2.27.3
[pip3] nvidia-nvjitlink-cu12==12.8.93
[pip3] nvidia-nvtx-cu12==12.8.90
[pip3] torch==2.8.0
[pip3] torchao==0.12.0
[pip3] triton==3.4.0
[conda] executorch 0.7.0 pypi_0 pypi
[conda] numpy 2.3.2 pypi_0 pypi
[conda] nvidia-cublas-cu12 12.8.4.1 pypi_0 pypi
[conda] nvidia-cuda-cupti-cu12 12.8.90 pypi_0 pypi
[conda] nvidia-cuda-nvrtc-cu12 12.8.93 pypi_0 pypi
[conda] nvidia-cuda-runtime-cu12 12.8.90 pypi_0 pypi
[conda] nvidia-cudnn-cu12 9.10.2.21 pypi_0 pypi
[conda] nvidia-cufft-cu12 11.3.3.83 pypi_0 pypi
[conda] nvidia-curand-cu12 10.3.9.90 pypi_0 pypi
[conda] nvidia-cusolver-cu12 11.7.3.90 pypi_0 pypi
[conda] nvidia-cusparse-cu12 12.5.8.93 pypi_0 pypi
[conda] nvidia-cusparselt-cu12 0.7.1 pypi_0 pypi
[conda] nvidia-nccl-cu12 2.27.3 pypi_0 pypi
[conda] nvidia-nvjitlink-cu12 12.8.93 pypi_0 pypi
[conda] nvidia-nvtx-cu12 12.8.90 pypi_0 pypi
[conda] torch 2.8.0 pypi_0 pypi
[conda] torchao 0.12.0 pypi_0 pypi
[conda] triton 3.4.0 pypi_0 pypi

cc @digantdesai @freddan80 @per @zingo @oscarandersson8218

Start with the import in executorch/backends/arm/tosa_quant_utils.py and compare it with the installation instructions in the linked getting-started documentation. Verify how the tosa dependency is expected to be provided, then confirm that importing EthosUPartitioner after installing executorch==0.7 no longer raises ModuleNotFoundError.