🍱 Build model inference APIs and multi-model serving systems with any open-source or custom AI models. 👉 Join our forum!
BentoML is a Python library for building online serving systems optimized for AI apps and model inference.
- 🍱 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.
- 👩💻 Fully customizable. Easily implement your own APIs or task queues, with custom business logic, model inference and multi-model composition. Supports any ML framework, modality, and inference runtime.
- 🚀 Ready for Production. Develop, run and debug locally. Seamlessly deploy to production with Docker containers or Kubernetes.
Install BentoML:
# Requires Python≥3.9
pip install -U bentoml
Define APIs in a service.py file.
import bentoml
@bentoml.service(
image=bentoml.images.Image(python_version="3.11").python_packages("torch", "transformers"),
)
class Summarization:
def __init__(self) -> None:
import torch
from transformers import pipeline
device = "cuda" if torch.cuda.is_available() else "cpu"
self.pipeline = pipeline('summarization', device=device)
@bentoml.api(batchable=True)
def summarize(self, texts: list[str]) -> list[str]:
results = self.pipeline(texts)
return [item['summary_text'] for item in results]Install PyTorch and Transformers packages to your Python virtual environment.
pip install torch transformers # additional dependencies for local runRun the service code locally (serving at http://localhost:3000 by default):
bentoml serveYou should expect to see the following output.
[INFO] [cli] Starting production HTTP BentoServer from "service:Summarization" listening on http://localhost:3000 (Press CTRL+C to quit)
[INFO] [entry_service:Summarization:1] Service Summarization initialized
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:
summarized_text: str = client.summarize([bentoml.__doc__])[0]
print(f"Result: {summarized_text}")Run bentoml build to package necessary code, models, dependency configs into a Bento - the standardized deployable artifact in BentoML:
bentoml buildEnsure Docker is running. Generate a Docker container image for deployment:
bentoml containerize summarization:latestRun the generated image:
docker run --rm -p 3000:3000 summarization:latest- LLMs: Llama 3.2, Mistral, DeepSeek Distil, and more.
- Image Generation: Stable Diffusion 3 Medium, Stable Video Diffusion, Stable Diffusion XL Turbo, ControlNet, and LCM LoRAs.
- Embeddings: SentenceTransformers and ColPali
- Audio: ChatTTS, XTTS, WhisperX, Bark
- Computer Vision: YOLO and ResNet
- Advanced examples: Function calling, LangGraph, CrewAI
Check out the full list for more sample code and usage.
- Model composition
- Workers and model parallelization
- Adaptive batching
- GPU inference
- Distributed serving systems
- Model loading and Model Store
- Observability
See Documentation for more tutorials and guides.
Get involved and join our Community Forum 💬, 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.
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 our forum.
Thanks to all of our amazing contributors!
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-trackOr by setting the environment variable:
export BENTOML_DO_NOT_TRACK=True