Quantize neural upscaling models with ExecuTorch
Introduction
Explore PTQ and QAT for ExecuTorch INT8 deployment
Set up your environment for ExecuTorch quantization
Apply PTQ and export a quantized VGF model
Apply QAT and export a quantized VGF model
Inspect the graph with Model Explorer
Next Steps

  Log an issue

  Fork and edit

  Discuss on Discord

Install and configure PyTorch, TorchAO, and ExecuTorch for quantization

In this section, you create a Python environment with PyTorch, TorchAO, and ExecuTorch components needed for quantization and .vgf export.

Note

If you already use Neural Graphics Model Gym , keep that environment and reuse it here.

Create a virtual environment

Create and activate a virtual environment:

    

        
        
python3 -m venv venv
source venv/bin/activate
python -m pip install --upgrade pip

Clone the ExecuTorch repository

In your virtual environment, clone the ExecuTorch repository and run the installation script:

    

        
        
git clone https://github.com/pytorch/executorch.git
cd executorch
./install_executorch.sh

Run the Arm backend setup script

From the root of the cloned executorch repository, run the Arm backend setup script:

    

        
        
./examples/arm/setup.sh \
  --i-agree-to-the-contained-eula \
  --disable-ethos-u-deps \
  --enable-mlsdk-deps

In the same terminal session, source the generated setup script so the Arm backend tools (including the model converter) are available on your PATH:

    

        
        
source ./examples/arm/arm-scratch/setup_path.sh

Verify the model converter is available:

    

        
        
command -v model-converter || command -v model_converter

Verify your imports:

    

        
        
import torch
import torchvision
import torchao

import executorch
import executorch.backends.arm
from executorch.backends.arm.vgf.partitioner import VgfPartitioner

print("torch:", torch.__version__)
print("torchvision:", torchvision.__version__)
print("torchao:", torchao.__version__)
Tip

If executorch.backends.arm is missing, you installed an ExecuTorch build without the Arm backend. Use an ExecuTorch build that includes executorch.backends.arm and the VGF partitioner.

If you checked out a specific ExecuTorch branch (for example, release/1.0) and you run into version mismatches, check out the main branch of ExecuTorch from the cloned repository and install from source:

    

        
        
pip install -e .

What you’ve accomplished and what’s next

In this section, you:

  • Created a Python virtual environment with PyTorch, TorchAO, and ExecuTorch
  • Ran the Arm backend setup script and verified the model converter is available on your PATH

In the next section, you apply PTQ to a sample model and generate a .vgf artifact.

Back
Next