### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### What happened?

Have been seeing a lot of OOM kills after upgrading docker image to [ghcr.io/berriai/litellm:main-v1.82.0-stable](http://ghcr.io/berriai/litellm:main-v1.82.0-stable) .

In earlier versions, pods used to have high memory spikes (OOM kills) during cleanup due to unefficient queries which was solved using [#21930](https://github.com/BerriAI/litellm/pull/21930)

Is there a possible solution to resolve this or some github issue around this?

<img width="2390" height="1058" alt="Image" src="https://github.com/user-attachments/assets/4bc0d2a4-839e-488f-bbd8-ee104f979969" />

### Steps to Reproduce

``` ... general_settings: # DB Settings proxy_batch_write_at: 10 database_connection_pool_limit: 10 store_prompts_in_spend_logs: true maximum_spend_logs_retention_period: 30d maximum_spend_logs_retention_interval: 1d store_model_in_db: true allow_requests_on_db_unavailable: true

# Health Check settings background_health_checks: true use_shared_health_check: true health_check_interval: …