> ## Documentation Index
> Fetch the complete documentation index at: https://tensorfuse.io/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Tensorfuse

> AI inference and finetuning on your AWS account

Tensorfuse is a serverless platform that deploys and scales AI models inside **your AWS account**. It handles the infrastructure so you can focus on building.

## Modalities you can deploy

Deploy and scale everything from large language models to specialized audio and video processors.

<CardGroup>
  <Card title="LLMs & SLMs" icon="message-bot" href="/guides/modality/text/openai_oss">
    Serve models like OpenAI OSS, Llama 3 or Mistral for chatbots, agents, and Retrieval-Augmented Generation.
  </Card>

  <Card title="Image & Video Generation" icon="camera" href="/guides/sd3_medium">
    Deploy text-to-image models like Stable Diffusion to generate visuals with a simple API call.
  </Card>

  <Card title="TTS and ASR models" icon="waveform" href="/guides/modality/audio/sesame-csm-1b">
    Build powerful speech-to-text services with Whisper or create realistic text-to-speech applications.
  </Card>

  <Card title="Custom Models" icon="puzzle-piece" href="/guides/jina_embeddings">
    Deploy your own custom trained models for any use case such as rerankers, embedders or voice activity detection.
  </Card>
</CardGroup>

***

## A Complete Platform for AI Workloads

Tensorfuse provides a single platform for the entire model lifecycle. It lets you:

* Serve models as [auto-scaling web endpoints](/concepts/deployments) that handle traffic spikes and scale to zero.
* Run [asynchronous jobs](/concepts/job_queues) for batch inference, data processing, or large-scale model evaluations.
* Launch [finetuning](/concepts/finetuning) runs on your own private data to create powerful, specialized models.
* Spin up [interactive GPU-powered development environments](/concepts/devcontainers) with your code pre-loaded for experimentation.
* Manage [project secrets](/concepts/secrets) and mount [persistent volumes](/concepts/volumes) for stateful applications.
* Automate your MLOps workflow using our [GitHub Actions](/concepts/github_actions) integration.

## How does it work?

Tensorfuse runs entirely inside your own AWS account.

It uses a secure **cross-account IAM** role to automatically provision and manage a dedicated **Kubernetes (EKS)** cluster within your VPC.

Unlike hosted platforms, your proprietary data and models never leave your cloud perimeter. You get the simplicity of a serverless platform with the security and control of owning your infrastructure—without having to manage any of it yourself.

***

## Get Started

<CardGroup>
  <Card title="Go to the Getting Started" icon="rocket" href="/concepts/getting_started_tensorkube">
    Install the CLI and deploy your first application in under 5 minutes.
  </Card>

  <Card title="Explore Examples on GitHub" icon="github" href="https://github.com/tensorfuse/tensorfuse-examples">
    Browse our repository of ready-to-deploy models for a wide variety of use cases.
  </Card>
</CardGroup>