Skip to content

Run Outlines using Modal

Modal is a serverless platform that allows you to easily run code on the cloud, including GPUs. It can come very handy for those of us who don't have a monster GPU at home and want to be able to quickly and easily provision, configure and orchestrate cloud infrastructure.

In this guide we will show you how you can use Modal to run programs written with Outlines on GPU in the cloud.

Build the image

First we need to define our container image. We download the Mistral-7B-v0.1 model from HuggingFace as part of the definition of the image so it only needs to be done once.

from modal import Image, Stub, gpu

stub = Stub(name="outlines-app")

outlines_image = Image.debian_slim(python_version="3.11").pip_install(

def import_model():
    import outlines

outlines_image = outlines_image.run_function(import_model)

We will run the JSON-structured generation example in the README, with the following schema:

Run inference

schema = """{
    "title": "Character",
    "type": "object",
    "properties": {
        "name": {
            "title": "Name",
            "maxLength": 10,
            "type": "string"
        "age": {
            "title": "Age",
            "type": "integer"
        "armor": {"$ref": "#/definitions/Armor"},
        "weapon": {"$ref": "#/definitions/Weapon"},
        "strength": {
            "title": "Strength",
            "type": "integer"
    "required": ["name", "age", "armor", "weapon", "strength"],
    "definitions": {
        "Armor": {
            "title": "Armor",
            "description": "An enumeration.",
            "enum": ["leather", "chainmail", "plate"],
            "type": "string"
        "Weapon": {
            "title": "Weapon",
            "description": "An enumeration.",
            "enum": ["sword", "axe", "mace", "spear", "bow", "crossbow"],
            "type": "string"

To make the inference work on Modal we need to wrap the corresponding function in a @stub.function decorator. We pass to this decorator the image and GPU on which we want this function to run (here an A100 with 80GB memory):

@stub.function(image=outlines_image, gpu=gpu.A100(memory=80))
def generate(
    prompt: str = "Amiri, a 53 year old warrior woman with a sword and leather armor.",
    import outlines

    model = outlines.models.transformers(
        "mistralai/Mistral-7B-v0.1", device="cuda"

    generator = outlines.generate.json(model, schema)
    character = generator(
        f"<s>[INST]Give me a character description. Describe {prompt}.[/INST]"


We then need to define a local_entrypoint to call our function generate remotely:

def main(
    prompt: str = "Amiri, a 53 year old warrior woman with a sword and leather armor.",

Here @stub.local_entrypoin() decorator defines main as the function to start from locally when running the Modal CLI. You can save above code to (or use this implementation). Let's now see how to run the code on the cloud using the Modal CLI.

Run on the cloud

First install the Modal client from PyPi:

pip install modal

You then need to obtain a token from Modal. To do so easily, run the following command:

modal setup

Once that is set you can run inference on the cloud using:

modal run

You should see the Modal app initialize, and soon after see the result of the print function in your terminal. That's it!