Home

Awesome

<div align="center"> <picture> <source media="(prefers-color-scheme: light)" srcset="/docs/exo-logo-black-bg.jpg"> <img alt="exo logo" src="/docs/exo-logo-transparent.png" width="50%" height="50%"> </picture>

exo: Run your own AI cluster at home with everyday devices. Maintained by exo labs.

<h3>

Discord | Telegram | X

</h3>

GitHub Repo stars Tests License: GPL v3

</div>

Forget expensive NVIDIA GPUs, unify your existing devices into one powerful GPU: iPhone, iPad, Android, Mac, Linux, pretty much any device!

<div align="center"> <h2>Update: exo is hiring. See <a href="https://exolabs.net">here</a> for more details.</h2> </div>

Get Involved

exo is experimental software. Expect bugs early on. Create issues so they can be fixed. The exo labs team will strive to resolve issues quickly.

We also welcome contributions from the community. We have a list of bounties in this sheet.

Features

Wide Model Support

exo supports different models including LLaMA (MLX and tinygrad), Mistral, LlaVA, Qwen and Deepseek.

Dynamic Model Partitioning

exo optimally splits up models based on the current network topology and device resources available. This enables you to run larger models than you would be able to on any single device.

Automatic Device Discovery

exo will automatically discover other devices using the best method available. Zero manual configuration.

ChatGPT-compatible API

exo provides a ChatGPT-compatible API for running models. It's a one-line change in your application to run models on your own hardware using exo.

Device Equality

Unlike other distributed inference frameworks, exo does not use a master-worker architecture. Instead, exo devices connect p2p. As long as a device is connected somewhere in the network, it can be used to run models.

Exo supports different partitioning strategies to split up a model across devices. The default partitioning strategy is ring memory weighted partitioning. This runs an inference in a ring where each device runs a number of model layers proportional to the memory of the device.

"A screenshot of exo running 5 nodes

Installation

The current recommended way to install exo is from source.

Prerequisites

Hardware Requirements

From source

git clone https://github.com/exo-explore/exo.git
cd exo
pip install -e .
# alternatively, with venv
source install.sh

Troubleshooting

Performance

  1. Upgrade to the latest version of MacOS 15.
  2. Run ./configure_mlx.sh. This runs commands to optimize GPU memory allocation on Apple Silicon Macs.

Documentation

Example Usage on Multiple MacOS Devices

Device 1:

exo

Device 2:

exo

That's it! No configuration required - exo will automatically discover the other device(s).

exo starts a ChatGPT-like WebUI (powered by tinygrad tinychat) on http://localhost:52415

For developers, exo also starts a ChatGPT-compatible API endpoint on http://localhost:52415/v1/chat/completions. Examples with curl:

Llama 3.2 3B:

curl http://localhost:52415/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
     "model": "llama-3.2-3b",
     "messages": [{"role": "user", "content": "What is the meaning of exo?"}],
     "temperature": 0.7
   }'

Llama 3.1 405B:

curl http://localhost:52415/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
     "model": "llama-3.1-405b",
     "messages": [{"role": "user", "content": "What is the meaning of exo?"}],
     "temperature": 0.7
   }'

Llava 1.5 7B (Vision Language Model):

curl http://localhost:52415/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
     "model": "llava-1.5-7b-hf",
     "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "What are these?"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "http://images.cocodataset.org/val2017/000000039769.jpg"
            }
          }
        ]
      }
    ],
     "temperature": 0.0
   }'

Example Usage on Multiple Heterogenous Devices (MacOS + Linux)

Device 1 (MacOS):

exo --inference-engine tinygrad

Here we explicitly tell exo to use the tinygrad inference engine.

Device 2 (Linux):

exo

Linux devices will automatically default to using the tinygrad inference engine.

You can read about tinygrad-specific env vars here. For example, you can configure tinygrad to use the cpu by specifying CLANG=1.

Example Usage on a single device with "exo run" command

exo run llama-3.2-3b

With a custom prompt:

exo run llama-3.2-3b --prompt "What is the meaning of exo?"

Model Storage

Models by default are stored in ~/.cache/huggingface/hub.

You can set a different model storage location by setting the HF_HOME env var.

Debugging

Enable debug logs with the DEBUG environment variable (0-9).

DEBUG=9 exo

For the tinygrad inference engine specifically, there is a separate DEBUG flag TINYGRAD_DEBUG that can be used to enable debug logs (1-6).

TINYGRAD_DEBUG=2 exo

Formatting

We use yapf to format the code. To format the code, first install the formatting requirements:

pip3 install -e '.[formatting]'

Then run the formatting script:

python3 format.py ./exo

Known Issues

/Applications/Python 3.x/Install Certificates.command

Inference Engines

exo supports the following inference engines:

Networking Modules