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

# Backends

> Modal (serverless) and Apptainer (local) backends for running boileroom models on GPU infrastructure.

boileroom supports two backends for executing models on GPUs. The user-facing API is **identical regardless of backend** — you call `.fold()` or `.embed()` the same way, and get the same output types back.

## Backend selection

Set the backend when creating a model:

```python theme={null}
from boileroom import ESMFold

# Serverless GPU via Modal (default)
model = ESMFold(backend="modal")

# Local GPU via Apptainer container
model = ESMFold(backend="apptainer")
```

## Modal backend

Modal provides serverless GPU execution. Your code runs locally, but the model inference runs on Modal's cloud GPUs. Containers scale to zero when idle and spin up on demand.

### Setup

1. Install Modal: `pip install modal`
2. Authenticate: `modal token new`
3. Use the model with `backend="modal"` (this is the default)

### GPU options

You can select a GPU type via the `device` parameter. See [Modal's pricing page](https://modal.com/pricing) for the full list of available GPUs, VRAM, and per-second pricing.

### Serverless scaling

* Containers cold-start when first called (may take 30-60 seconds)
* Subsequent calls reuse warm containers
* Containers automatically scale down after a period of inactivity

## Apptainer backend

Apptainer (formerly Singularity) runs models in a container on your local machine or HPC cluster. This is useful when you need local execution, cannot use cloud services, or are running on institutional compute.

### Setup

1. Install Apptainer on your system
2. Use `backend="apptainer"` or `backend="apptainer:tag"` to specify a Docker image tag

### Tag syntax

By default, the Apptainer backend uses the installed Boileroom package version on the default CUDA line. You can still specify an explicit image tag when needed:

```python theme={null}
# Use the image tag matching the installed boileroom package version
model = ESMFold(backend="apptainer")

# Use a specific version tag
model = ESMFold(backend="apptainer:0.3.0")

# Use an explicit CUDA-qualified image tag
model = ESMFold(backend="apptainer:cuda11.8-0.3.0")
```

### Local execution

The Apptainer backend runs the model on your local GPU. Ensure you have a CUDA-compatible GPU with sufficient VRAM for the model.

## Context manager

Both backends support context manager usage to ensure proper cleanup:

```python theme={null}
with ESMFold(backend="modal") as model:
    result = model.fold("MKTVRQERLKSIVRI")
# Backend resources are automatically released
```

Without a context manager, the backend is cleaned up when the `ModelWrapper` instance is garbage collected or when the Python process exits.

## Device selection

The `device` parameter works the same way across backends:

```python theme={null}
# Let the backend auto-select (default: "cuda:0" if available)
model = ESMFold(backend="modal")

# Specify a device
model = ESMFold(backend="modal", device="cuda:0")

# Force CPU execution
model = ESMFold(backend="modal", device="cpu")
```