Model Runner

The backend library for the Docker Model Runner.

Overview

Note

This package is still under rapid development and its APIs should not be considered stable.

This package supports the Docker Model Runner in Docker Desktop (in conjunction with Model Distribution and the Model CLI). It includes a main.go that mimics its integration with Docker Desktop and allows the package to be run in a standalone mode.

Using the Makefile

This project includes a Makefile to simplify common development tasks. It requires Docker Desktop >= 4.41.0 The Makefile provides the following targets:

• build - Build the Go application
• run - Run the application locally
• clean - Clean build artifacts
• test - Run tests
• docker-build - Build the Docker image
• docker-run - Run the application in a Docker container with TCP port access and mounted model storage
• help - Show available targets

Running in Docker

The application can be run in Docker with the following features enabled by default:

• TCP port access (default port 8080)
• Persistent model storage in a local models directory

# Run with default settings
make docker-run

# Customize port and model storage location
make docker-run PORT=3000 MODELS_PATH=/path/to/your/models

This will:

• Create a models directory in your current working directory (or use the specified path)
• Mount this directory into the container
• Start the service on port 8080 (or the specified port)
• All models downloaded will be stored in the host's models directory and will persist between container runs

llama.cpp integration

The Docker image includes the llama.cpp server binary from the docker/docker-model-backend-llamacpp image. You can specify the version of the image to use by setting the LLAMA_SERVER_VERSION variable. Additionally, you can configure the target OS, architecture, and acceleration type:

# Build with a specific llama.cpp server version
LLAMA_SERVER_VERSION=v0.0.4-rc2-cpu make docker-build

# Specify all parameters
LLAMA_SERVER_VERSION=v0.0.4-rc2-cpu TARGET_OS=linux TARGET_ARCH=amd64 ACCEL=cpu make docker-build

Default values:

• LLAMA_SERVER_VERSION: v0.0.4-rc2-cpu
• TARGETOS: linux
• TARGETARCH: amd64
• ACCEL: cpu

The binary path in the image follows this pattern: /com.docker.llama-server.native.${TARGETOS}.${ACCEL}.${TARGETARCH}

API Examples

The Model Runner exposes a REST API that can be accessed via TCP port. You can interact with it using curl commands.

Using the API

When running with docker-run, you can use regular HTTP requests:

# List all available models
curl http://localhost:8080/models

# Create a new model
curl http://localhost:8080/models/create -X POST -d '{"from": "ai/smollm2"}'

# Get information about a specific model
curl http://localhost:8080/models/ai/smollm2

# Chat with a model
curl http://localhost:8080/engines/llama.cpp/v1/chat/completions -X POST -d '{
  "model": "ai/smollm2",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello, how are you?"}
  ]
}'

# Delete a model
curl http://localhost:8080/models/ai/smollm2 -X DELETE

The response will contain the model's reply:

{
  "id": "chat-12345",
  "object": "chat.completion",
  "created": 1682456789,
  "model": "ai/smollm2",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I'm doing well, thank you for asking! How can I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 16,
    "total_tokens": 40
  }
}