Deploy Pruna models

pruna offers deployment integrations with the following tools to supercharge your workflows.

Pruna is the bridge to the broader AI ecosystem, making sure your optimized models run smoothly across popular deployment and inference platforms. Whether you’re running on Docker, deploying with TritonServer, or serving with vLLM, Pruna fits right in.

Docker

Deploy Pruna in Docker containers for reproducible, GPU-accelerated environments.

docker_tutorial.rst

NVIDIA Triton Server

Production-scale AI deployments with scalable inference.

tritonserver.rst

vLLM

High-performance LLM serving with model-level optimizations.

vllm.rst

AWS AMI

Amazon machine images for running models.

ami.rst

Replicate

An inference platform for running machine learning models in production.

replicate.rst

Koyeb

A platform for running machine learning models in production.

koyeb.rst

Lightning AI LitServe

A flexible serving engine for AI models built on FastAPI to self-host and serve models.

litserve.rst