Configuring OliveSystem¶

This document describes how to configure the different types of OliveSystems

Local System¶

{
    "type": "LocalSystem",
    "config": {
        "device": "cpu"
    }
}

from olive.systems.local import LocalSystem
from olive.system.common import Device

local_system = LocalSystem(device=Device.CPU)

Please refer to LocalTargetUserConfig for more details on the config options.

AzureML System¶

Prerequisites¶

azureml extra dependencies installed.

pip install olive-ai[azureml]

or

pip install azure-ai-ml azure-identity

2. AzureML Workspace with necessary compute created. Refer to this for more details. Download the workspace config json.

3. AzureML authentication credentials. Refer to this for more details.

System Configuration¶

{
    "type": "AzureML",
    "config": {
        "aml_config_path": "olive-workspace-config.json",
        "aml_compute": "cpu-cluster",
        "aml_docker_config": {
            "base_image": "mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu20.04",
            "conda_file_path": "conda.yaml"
        }
    }
}

from olive.systems.azureml import AzureMLDockerConfig, AzureMLSystem

docker_config = AzureMLDockerConfig(
    base_image="mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu20.04",
    conda_file_path="conda.yaml",
)
aml_system = AzureMLSystem(
    aml_config_path="olive-workspace-config.json",
    aml_compute="cpu-cluster",
    aml_docker_config={
            "base_image": "mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu20.04",
            "conda_file_path": "conda.yaml"
        }
)

Please refer to this example for "conda.yaml".

Important

The AzureML environment must have olive-ai installed!

Please refer to AzureMLTargetUserConfig for more details on the config options.

Docker System¶

Prerequisites¶

Docker Engine installed on the host machine.

docker extra dependencies installed.

pip install olive-ai[docker]

or

pip install docker

System Configuration¶

{
    "type": "Docker",
    "config": {
        "local_docker_config": {
            "image_name": "olive",
            "build_context_path": "docker",
            "dockerfile": "Dockerfile"
        }
    }
}

from olive.systems.docker import DockerSystem, LocalDockerConfig

local_docker_config = LocalDockerConfig(
    image_name="olive",
    build_context_path="docker",
    dockerfile="Dockerfile",
)
docker_system = DockerSystem(local_docker_config=local_docker_config)

Please refer to this example for "docker" and "Dockerfile".

Important

The docker container must have olive-ai installed!

Please refer to DockerTargetUserConfig for more details on the config options.

Python Environment System¶

{
    "type": "PythonEnvironment",
    "config": {
        "python_environment_path": "/home/user/.virtualenvs/myenv",
        "device": "cpu"
    }
}

from olive.systems.python_environment import PythonEnvironmentSystem
from olive.system.common import Device

python_environment_system = PythonEnvironmentSystem(
    python_environment_path = "/home/user/.virtualenvs/myenv",
    device = Device.CPU
)

Important

The python environment system can only be used to evaluate onnx models. It must have onnxruntime installed!

Please refer to PythonEnvironmentTargetUserConfig for more details on the config options.