Ultrafast AI Inference

Scalable Infrastructure for Running Your AI Workloads at Scale

Installation

pip install beam-client

Features

• Extremely Fast: Launch containers in 200ms using a custom runc runtime
• Parallelization and Concurrency: Fan out workloads to 100s of containers
• First-Class Developer Experience: Hot-reloading, webhooks, and scheduled jobs
• Scale-to-Zero: Workloads are serverless by default
• Volume Storage: Mount distributed storage volumes
• GPU Support: Run on our cloud (4090s, H100s, and more) or bring your own GPUs

Quickstart

1. Create an account at https://beam.cloud
2. Follow our Getting Started Guide

Creating your first inference endpoint

With Beam, everything is Python-native—no YAML, no config files, just code:

from beam import Image, endpoint


@endpoint(
    image=Image(python_version="python3.11"),
    gpu="A10G",
    cpu=1,
    memory=1024,
)
def handler():
    return {"label": "cat", "confidence": 0.97}

This snippet deploys your code to a GPU-backed container with an HTTPS endpoint—ready to serve requests immediately (https://my-model-v1.app.beam.cloud/)

Self-Hosting vs Cloud

Beta9 is the open-source engine powering Beam, our fully-managed cloud platform. You can self-host Beta9 for free or choose managed cloud hosting through Beam.

Contributing

We welcome contributions big or small. These are the most helpful things for us:

• Submit a feature request or bug report
• Open a PR with a new feature or improvement

Thanks to Our Contributors