Serve and deploy apps

Flyte provides two main ways to deploy apps: serve (for development) and deploy (for production). This section covers both methods and their differences.

Serve vs deploy

`flyte serve`

Serving is designed for development and iteration:

Dynamic parameter modification: You can override app parameters when serving
Quick iteration: Faster feedback loop for development
Interactive: Better suited for testing and experimentation

`flyte deploy`

Deployment is designed for production use:

Immutable: Apps are deployed with fixed configurations
Production-ready: Optimized for stability and reproducibility

Using Python SDK

Serve

Deploy

serve_and_deploy_examples.py
                
app_env = flyte.app.AppEnvironment(
    name="my-app",
    image=flyte.app.Image.from_debian_base().with_pip_packages("streamlit==1.41.1"),
    args=["streamlit", "hello", "--server.port", "8080"],
    port=8080,
    resources=flyte.Resources(cpu="1", memory="1Gi"),
)

if __name__ == "__main__":
    flyte.init_from_config()
    app = flyte.serve(app_env)
    print(f"Served at: {app.url}")

serve_and_deploy_examples.py
                
app_env = flyte.app.AppEnvironment(
    name="my-app",
    image=flyte.app.Image.from_debian_base().with_pip_packages("streamlit==1.41.1"),
    args=["streamlit", "hello", "--server.port", "8080"],
    port=8080,
    resources=flyte.Resources(cpu="1", memory="1Gi"),
)

if __name__ == "__main__":
    flyte.init_from_config()
    deployments = flyte.deploy(app_env)
    # Access deployed app URL from the deployment
    for deployed_env in deployments[0].envs.values():
        print(f"Deployed: {deployed_env.deployed_app.url}")

Using the CLI

Serve

Deploy

flyte serve path/to/app.py app_env

flyte deploy path/to/app.py app_env

Next steps

How app serving works: Understanding the serve process and configuration options
How app deployment works: Understanding the deploy process and configuration options
Activating and deactivating apps: Managing app lifecycle
Basic project: Build a RAG embedding pipeline and semantic search app with Streamlit
Prefetching models: Download and shard HuggingFace models for vLLM and SGLang

How app serving worksWhat flyte.serve does, and why its faster feedback loop suits development.How app custom domains workPoint a custom domain at an app.How app deployment worksWhat flyte.deploy does, and why versioned immutable deployments are the production path.Activating and deactivating appsTurn a deployed app on and off, and what activation means for each deploy method.Prefetching modelsDownload and shard a HuggingFace model before an inference app starts.