---
title: "Discussion on \"Can we have a scalable fastapi service with common cache ?\" | Hashnode"
description: "Discussion on \"Can we have a scalable fastapi service with common cache ?\". So as it goes, we were using FastAPI for one of the apps. Our app uses a lot of memory(for ml models).\nPremise: I wanted to launch multiple workers of the app as Python is single-threaded and also be able to have a common cache across.\nWe can use Uvi..."
url: "https://hashnode.com/posts/can-we-have-a-scalable-fastapi-service-with-common-cache/64d152361e3c5b9fe165b120"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Can we have a scalable fastapi service with common cache ?](https://engineering.oohalo.com/can-we-have-a-scalable-fastapi-service-with-common-cache?utm_source=hashnode&utm_medium=feed)

So as it goes, we were using FastAPI for one of the apps. Our app uses a lot of memory(for ml models). Premise: I wanted to launch multiple workers of the app as Python is single-threaded and also be able to have a common cache across. We can use Uvi...

Dec 11, 2022 · 3 min read · engineering.oohalo.com  
Read the article

-   [#fastapi](https://hashnode.com/tag/fastapi)
-   [#cache](https://hashnode.com/tag/cache)
-   [#workers](https://hashnode.com/tag/workers)

## Written by

[K](https://hashnode.com/@kiranhere)

@kiranhere

  
[View profile](https://hashnode.com/@kiranhere)

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
