BerriAI/litellm

[Bug]: tpm/rmp of llm model not managed by litellm in memoryb redis cluster

Opened this issue · 1 comments

What happened?

i have impletemented the aws memorydb redis cluster for production env to manage tpm/rpm but in redis cluster i am not able to see any data. it is showing empty array in redis cluster on port 1992. please any info regarding this will be helpful
Screenshot 2024-11-05 at 9 38 35 PM

Relevant log output

No response

Twitter / LinkedIn details

No response

@ishaan-jaff @krrishdholakia
Adding to this, just a quick question
We have set up Redis caching in the LiteLLM_settings for our proxy, which is deployed on AWS ECS/Fargate with multiple replicas. My question is, do I need to also define Redis caching details separately in the router_settings, or is the existing Redis configuration in LiteLLM_settings is sufficient across all replicas? Would it be necessary to create a separate Redis cluster specifically for the router?
Thanks in advance for your guidance!