Skip to main content

Neural network model compiler for Arm Ethos-U NPUs

Project description


This tool is used to compile a TensorFlow Lite for Microcontrollers neural network model into an optimised version that can run on an embedded system containing an Arm Ethos-U NPU.

In order to be accelerated by the Ethos-U NPU the network operators must be quantised to either 8-bit (unsigned or signed) or 16-bit (signed).

The optimised model will contain TensorFlow Lite Custom operators for those parts of the model that can be accelerated by the Ethos-U NPU. Parts of the model that cannot be accelerated are left unchanged and will instead run on the Cortex-M series CPU using an appropriate kernel (such as the Arm optimised CMSIS-NN kernels).

After compilation the optimised model can only be run on an Ethos-U NPU embedded system.

The tool will also generate performance estimates (EXPERIMENTAL) for the compiled model.

TensorFlow Support

  • Vela 2.1.0 to current supports TensorFlow 2.4
  • Vela 2.0.0 to 2.0.1 supports TensorFlow 2.3
  • Vela 0.1.0 to 1.2.0 supports TensorFlow 2.1


Vela runs on the Linux and Microsoft Windows 10 operating systems, see note in Installation section below.


The following should be installed prior to the installation of Vela:

  • Python >= 3.6
  • Pip3
  • GNU toolchain (GCC, Binutils and libraries)

And optionally:

  • Pipenv virtual environment tool


Vela is available to install as a package from PyPi, or as source code from ML Platform. Both methods will automatically install all the required dependencies.

Note: For installing on Microsoft Windows 10 you need to have a C99 capable toolchain installed. The recommended and tested toolchain is Microsoft Visual C++ 14.2 Build Tools, see


Install Vela from PyPi using the following command:

pip3 install ethos-u-vela

ML Platform

First obtain the source code by either downloading the desired TGZ file from:

Or by cloning the git repository:

git clone

Once you have the source code, Vela can be installed using the following command:

pip3 install .

Or, if you use pipenv:

pipenv install .

Advanced Installation for Developers

If you plan to modify the Vela codebase then it is recommended to install Vela as an editable package to avoid the need to re-install after every modification. This is done by adding the -e option to the above install commands like so:

pip3 install -e .

Or, if you use pipenv:

pipenv install -e .

If you plan to contribute to the Vela project (highly encouraged!) then it is recommended to install Vela along with the pre-commit tools (see Vela Testing for more details).


Vela is run with an input .tflite file passed on the command line. This file contains the neural network to be compiled. The tool then outputs an optimised version with a _vela.tflite file prefix, along with the performance estimate (EXPERIMENTAL) CSV files, all to the output directory. It also prints a performance estimation summary back to the console, see Vela Performance Estimation Summary.

If you use the pipenv virtual environment tool then first start by spawning a shell in the virtual environment:

pipenv shell

After which running Vela is the same regardless of whether you are in a virtual environment or not.

Example usage:

  1. Compile the network my_model.tflite. The optimised version will be output to ./output/my_network_vela.tflite.
vela my_model.tflite
  1. Compile the network /path/to/my_model.tflite and specify the output to go in the directory ./results_dir/.
vela --output-dir ./results_dir /path/to/my_model.tflite
  1. Compile a network using a particular Ethos-U NPU. The following command selects an Ethos-U65 NPU accelerator configured with 512 MAC units.
vela --accelerator-config ethos-u65-512 my_model.tflite
  1. Compile a network using a particular embedded system configuration defined in Vela's configuration file. The following command selects the My_Sys_Config system configuration along with the My_Mem_Mode memory mode from the vela_cfg.ini configuration file.
vela --config vela_cfg.ini --system-config My_Sys_Config --memory-mode My_Mem_Mode my_model.tflite
  1. To get a list of all available options (see CLI Options section below):
vela --help


When running the Vela compiler it may report a number of warning messages to the console. These should all be thoroughly reviewed as they will indicate decisions that the compiler has made in order to create the optimised network.

Example Networks

Some example networks that contain quantised operators which can be compiled by Vela to run on the Ethos-U NPU can be found at:


Please see Vela External APIs.


Please see Vela Contributions.

Debug Database

Please see Vela Debug Database.


Please see Vela CLI Options. This includes a description of the system configuration file format.


Please see Vela Performance Estimation Summary.


Please see Vela Releases.


Please see Vela Security.

Supported Operators

Please see Vela Supported Operators for the list of operators supported in this release.


Please see Vela Testing.


Additional useful information:


Vela is licensed under Apache License 2.0.

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ethos-u-vela-3.0.0.tar.gz (285.5 kB view hashes)

Uploaded source

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page