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

# b10cache

> Persist data across replicas or deployments

<Note>
  Use b10cache for files your model writes at runtime that other replicas can reuse, such as [`torch.compile` artifacts](/development/model/torch-compile-cache). For read-only weights known at deploy time, use [BDN](/development/model/bdn). For more information, see [Data and storage](/development/model/data-directory).
</Note>

## Overview

Deployments sometimes produce files that are useful to other replicas. Using `torch.compile`, for example, produces a cache that can speed up future `torch.compile` calls on the same function, reducing cold start time for other replicas.

b10cache stores these files. It's a volume mounted over the network onto each of your pods, with two scopes:

### Organization scope: `/cache/org/`

Shared across every pod you deploy in your organization. Move a file into this directory and any pod can read it.

### Deployment scope: `/cache/model/`

Shared across every pod within a single deployment. Use this scope to keep deployment filesystems isolated.

<Danger>
  ### Not persistent object storage

  b10cache is reliable, but treat it as a cache, not a database. Always have a fallback path that runs if the file isn't there yet. For example, the first replica of a new deployment writes to b10cache rather than reading from it.
</Danger>

## Related features

For more information, see [Torch compile caching](/development/model/torch-compile-cache), which uses b10cache to persist `torch.compile` artifacts across replicas.