README.md

Unified Model Serving Framework

🍱 Build model inference APIs and multi-model serving systems with any open-source or custom AI models. 👉 Join our Slack community!

What is BentoML?

BentoML is an open-source model serving framework, simplifying how AI/ML models gets into production:

• 🍱 Easily build APIs for Any AI/ML Model. Turn any model inference script into a REST API server with just a few lines of code and standard Python type hints.
• 🐳 Docker Containers made simple. No more dependency hell! Manage your environments, dependencies and model versions with a simple config file. BentoML automatically generates Docker images, ensures reproducibility, and simplifies how you deploy to different environments.
• 🧭 Maximize CPU/GPU utilization. Build high performance inference APIs leveraging built-in serving optimization features like dynamic batching, model parallelism, multi-stage pipeline and multi-model inference-graph orchestration.
• 👩‍💻 Build Custom AI Applications. Easily implement your own API specifications, asynchronous inference tasks; customize pre/post-processing, model inference and model composition logic, all using Python code. Supports any ML framework, modality, and inference runtime.
• 🚀 Ready for Production. Develop, run and debug locally. Seamlessly deploy to production with Docker containers or BentoCloud.

Getting started

Install BentoML:

# Requires Python≥3.8
pip install -U bentoml
pip install torch transformers  # additional dependencies for demo purpose

Define APIs in a service.py file.

from __future__ import annotations

import bentoml
from typing import List

@bentoml.service
class Summarization:
    def __init__(self) -> None:
        from transformers import pipeline
        self.pipeline = pipeline('summarization')

    @bentoml.api(batchable=True)
    def summarize(self, texts: List[str]) -> List[str]:
        results = self.pipeline(texts)
        return [item['summary_text'] for item in results]

Run the service code locally (serving at http://localhost:3000 by default):

bentoml serve service.py:Summarization

Now you can run inference from your browser at http://localhost:3000 or with a Python script:

import bentoml

with bentoml.SyncHTTPClient('http://localhost:3000') as client:
    text_to_summarize: str = input("Enter text to summarize: ")
    summarized_text: str = client.summarize([text_to_summarize])[0]
    print(f"Summarized text: {summarized_text}")

Deploying your first Bento

To deploy your BentoML Service code, first create a bentofile.yaml file to define its dependencies and environments. Find the full list of bentofile options here.

service: "service:Summarization" # Entry service import path
include:
  - "*.py" # Include all .py files in current directory
python:
  lock_packages: false # option to lock versions found in current environment
  packages: # Python dependencies to include
  - torch
  - transformers

Then, choose one of the following ways for deployment:

🐳 Docker Container

Run bentoml build to package necessary code, models, dependency configs into a Bento - the standardized deployable artifact in BentoML:

bentoml build

Ensure Docker is running. Generate a Docker container image for deployment:

bentoml containerize summarization:latest

Run the generated image:

docker run --rm -p 3000:3000 summarization:latest

☁️ BentoCloud

BentoCloud is the AI inference platform for fast moving AI teams. It lets you easily deploy your BentoML code in a fast-scaling infrastructure. Sign up for BentoCloud for personal access; for enterprise use cases, contact our team.

# After signup, follow login instructions upon API token creation:
bentoml cloud login --api-token <your-api-token>

# Deploy from current directory:
bentoml deploy .

For detailed explanations, read Quickstart.

Use cases

• LLMs: Llama 3, Mixtral, Solar, Mistral, and more
• Image Generation: Stable Diffusion, Stable Video Diffusion, Stable Diffusion XL Turbo, ControlNet, LCM LoRAs
• Text Embeddings: SentenceTransformers
• Audio: ChatTTS, XTTS, WhisperX, Bark
• Computer Vision: YOLO
• Multimodal: BLIP, CLIP
• RAG: RAG-as-a-Service with custom models

Check out the examples folder for more sample code and usage.

Advanced topics

• Model composition
• Workers and model parallelization
• Adaptive batching
• GPU inference
• Distributed serving systems
• Concurrency and autoscaling
• Model packaging and Model Store
• Observability
• BentoCloud deployment

See Documentation for more tutorials and guides.

Community

Get involved and join our Community Slack 💬, where thousands of AI/ML engineers help each other, contribute to the project, and talk about building AI products.

To report a bug or suggest a feature request, use GitHub Issues.

Contributing

There are many ways to contribute to the project:

• Report bugs and "Thumbs up" on issues that are relevant to you.
• Investigate issues and review other developers' pull requests.
• Contribute code or documentation to the project by submitting a GitHub pull request.
• Check out the Contributing Guide and Development Guide to learn more.
• Share your feedback and discuss roadmap plans in the #bentoml-contributors channel here.

Thanks to all of our amazing contributors!

Usage tracking and feedback

The BentoML framework collects anonymous usage data that helps our community improve the product. Only BentoML's internal API calls are being reported. This excludes any sensitive information, such as user code, model data, model names, or stack traces. Here's the code used for usage tracking. You can opt-out of usage tracking by the --do-not-track CLI option:

bentoml [command] --do-not-track

Or by setting the environment variable:

export BENTOML_DO_NOT_TRACK=True

License

Apache License 2.0